1
250W 짜리를 그대로 사용할 경우
125W로 제한할 경우
30토큰이나 35토큰이나 비슷하다고 생각하면 비슷한 수준이라
전기는 절반만 먹고 약간느려지는 수준이라면 나쁘지 않은 설정인듯
| llama-server web ui (0) | 2026.04.24 |
|---|---|
| llama.cpp on windows / cuda vs vulkan (0) | 2026.04.24 |
| vscode continue.dev (0) | 2026.04.24 |
| RAG - Retrieval-Augmented Generation (0) | 2026.04.24 |
| llama.cpp on ubuntu with 1060 6GB (0) | 2026.04.23 |
llama.cpp의 llama-server 로 구동하면 모델은 바꿀수 없지만
chatGPT 나 claude와 유사한 web ui로 사용할 수 있다.
간략하게 토큰 생성 속도도 나온다.
설정은 다음과 같다.
| nvidia-smi를 통한 소비전력 제한과 토큰 생성속도 (1) | 2026.04.24 |
|---|---|
| llama.cpp on windows / cuda vs vulkan (0) | 2026.04.24 |
| vscode continue.dev (0) | 2026.04.24 |
| RAG - Retrieval-Augmented Generation (0) | 2026.04.24 |
| llama.cpp on ubuntu with 1060 6GB (0) | 2026.04.23 |
두 개 성능 차이가 있을줄 알았는데(cuda가 높을줄..)
거의 오차범위 내에서 동일하게 나왔다.
그럼. 리눅스에서도 cuda 빌드 안해도 쓸만하다는걸려나?
근데 1080 ti 라서 그런가 cuda 13 버전은 오작동하고 12 버전으로 성공함
| D:\study\llm\llama-b8916-bin-win-cuda-13.1-x64>llama-cli.exe -m ..\gemma-4-E2B-it-Q4_K_M.gguf ggml_cuda_init: found 1 CUDA devices (Total VRAM: 11263 MiB): Device 0: NVIDIA GeForce GTX 1080 Ti, compute capability 6.1, VMM: yes, VRAM: 11263 MiB load_backend: loaded CUDA backend from D:\study\llm\llama-b8916-bin-win-cuda-13.1-x64\ggml-cuda.dll load_backend: loaded RPC backend from D:\study\llm\llama-b8916-bin-win-cuda-13.1-x64\ggml-rpc.dll load_backend: loaded CPU backend from D:\study\llm\llama-b8916-bin-win-cuda-13.1-x64\ggml-cpu-haswell.dll Loading model... /ggml_cuda_compute_forward: SCALE failed CUDA error: no kernel image is available for execution on the device current device: 0, in function ggml_cuda_compute_forward at D:\a\llama.cpp\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.cu:2962 err D:\a\llama.cpp\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.cu:97: CUDA error |
gemma4 e2b 모델인데 2.89GB 짜리이고 제법 정직하게 용량을 먹는 느낌.
| Fri Apr 24 22:57:19 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 582.28 Driver Version: 582.28 CUDA Version: 13.0 | +-----------------------------------------+------------------------+----------------------+ | GPU Name Driver-Model | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce GTX 1080 Ti WDDM | 00000000:01:00.0 Off | N/A | | 27% 39C P8 11W / 250W | 2936MiB / 11264MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1400 C+G ...-win-vulkan-x64\llama-cli.exe N/A | | 0 N/A N/A 1452 C ...al\Programs\Ollama\ollama.exe N/A | | 0 N/A N/A 9728 C+G ...em32\Kinect\KinectService.exe N/A | | 0 N/A N/A 13036 C+G ...s\Win64\EpicGamesLauncher.exe N/A | +-----------------------------------------------------------------------------------------+ |
| D:\study\llm\llama-b8918-bin-win-cuda-12.4-x64>llama-cli.exe -m ..\gemma-4-E2B-it-Q4_K_M.gguf ggml_cuda_init: found 1 CUDA devices (Total VRAM: 11263 MiB): Device 0: NVIDIA GeForce GTX 1080 Ti, compute capability 6.1, VMM: yes, VRAM: 11263 MiB load_backend: loaded CUDA backend from D:\study\llm\llama-b8918-bin-win-cuda-12.4-x64\ggml-cuda.dll load_backend: loaded RPC backend from D:\study\llm\llama-b8918-bin-win-cuda-12.4-x64\ggml-rpc.dll load_backend: loaded CPU backend from D:\study\llm\llama-b8918-bin-win-cuda-12.4-x64\ggml-cpu-haswell.dll Loading model... ▄▄ ▄▄ ██ ██ ██ ██ ▀▀█▄ ███▄███▄ ▀▀█▄ ▄████ ████▄ ████▄ ██ ██ ▄█▀██ ██ ██ ██ ▄█▀██ ██ ██ ██ ██ ██ ██ ██ ▀█▄██ ██ ██ ██ ▀█▄██ ██ ▀████ ████▀ ████▀ ██ ██ ▀▀ ▀▀ build : b8918-e583f3b4f model : gemma-4-E2B-it-Q4_K_M.gguf modalities : text available commands: /exit or Ctrl+C stop or exit /regen regenerate the last response /clear clear the chat history /read <file> add a text file /glob <pattern> add text files using globbing pattern > 안녕? 안녕하세요! 저는 사용자님을 돕기 위해 여기 있습니다. 😊 궁금한 점이 있으시거나 도움이 필요하시면 언제든지 말씀해 주세요! [ Prompt: 182.3 t/s | Generation: 84.7 t/s ] > 헬로? [Start thinking] Thinking Process: 1. **Analyze the input:** The user input is "헬로?" (Hello?). It's a very informal greeting, essentially a variation of "Hello?". 2. **Determine the context:** This is a casual interaction following a previous greeting ("안녕?" -> "안녕하세요!"). The user is acknowledging or testing the connection. 3. **Formulate the response strategy:** * Acknowledge the greeting warmly. * Match the casual tone (but remain polite and helpful). * Reiterate availability. * Invite further interaction. 4. **Draft potential responses (in Korean):** * (Option 1 - Simple echo): 네, 안녕하세요. (Yes, hello.) * (Option 2 - Enthusiastic): 네, 안녕하세요! 또 무엇을 도와드릴까요? (Yes, hello! What else can I help you with?) * (Option 3 - Casual/Friendly): 네! 저는 준비되어 있습니다. 😊 (Yes! I am ready.) 5. **Select the best response:** Option 2 is the most effective as it confirms the interaction and immediately prompts the user to state their need, moving the conversation forward. 6. **Final Polish:** (Translate the chosen response into natural Korean.) [End thinking] 네, 안녕하세요! 😊 저는 언제든지 사용자님의 질문에 답하거나 필요한 정보를 제공해 드릴 준비가 되어 있습니다. 궁금한 것이 있으신가요? [ Prompt: 321.5 t/s | Generation: 84.8 t/s ] > 으아앙 [Start thinking] Thinking Process: 1. **Analyze the input:** The user input is "으아앙" (Eu-aang). 2. **Determine the nature of the input:** "으아앙" is an interjection or sound, often used to express various emotions (pain, excitement, frustration, distress, playful sounds, etc.). In this context, it's highly informal and emotional. 3. **Assess the context:** The previous interactions were simple greetings ("안녕?", "헬로?"). The current input is a sudden, emotional expression. 4. **Determine the appropriate response strategy:** * Since the input is purely emotional and doesn't pose a question or request a task, the response should be empathetic, neutral, and open-ended. * The tone should be gentle and non-judgmental. * Acknowledge the emotion without demanding further explanation, allowing the user to guide the conversation. 5. **Draft potential responses (in Korean):** * *Option A (Direct inquiry):* 무슨 일 있으세요? (What's going on?) - A bit too direct. * *Option B (Empathy + Open invitation):* 무슨 일이 있으신가요? 괜찮으세요? (Is something happening? Are you okay?) - Good balance. * *Option C (Simple acknowledgment):* 네? (Yes?) / 어떠세요? (How are you?) - Too brief. 6. **Select and refine the best response (B is the most helpful):** Acknowledge the sound/feeling and gently ask if the user needs assistance or wants to talk about it. 7. **Final Check:** The response is safe, empathetic, and keeps the door open for the user to continue the conversation on their terms. (Self-correction: Avoid sounding too robotic. Keep the tone friendly.) [End thinking] 무슨 일이 있으신가요? 😊 혹시 힘든 일이 있으시거나, 이야기하고 싶으신 것이 있다면 편하게 말씀해 주세요. 제가 들어드릴게요. [ Prompt: 1014.9 t/s | Generation: 84.9 t/s ] > Exiting... common_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted | common_memory_breakdown_print: | - CUDA0 (GTX 1080 Ti) | 11263 = 7192 + (2981 = 1407 + 780 + 793) + 1090 | common_memory_breakdown_print: | - Host | 2037 = 1756 + 0 + 281 | |
| D:\study\llm\llama-b8916-bin-win-vulkan-x64>llama-cli.exe -m ..\gemma-4-E2B-it-Q4_K_M.gguf load_backend: loaded RPC backend from D:\study\llm\llama-b8916-bin-win-vulkan-x64\ggml-rpc.dll load_backend: loaded Vulkan backend from D:\study\llm\llama-b8916-bin-win-vulkan-x64\ggml-vulkan.dll load_backend: loaded CPU backend from D:\study\llm\llama-b8916-bin-win-vulkan-x64\ggml-cpu-haswell.dll Loading model... ▄▄ ▄▄ ██ ██ ██ ██ ▀▀█▄ ███▄███▄ ▀▀█▄ ▄████ ████▄ ████▄ ██ ██ ▄█▀██ ██ ██ ██ ▄█▀██ ██ ██ ██ ██ ██ ██ ██ ▀█▄██ ██ ██ ██ ▀█▄██ ██ ▀████ ████▀ ████▀ ██ ██ ▀▀ ▀▀ build : b8916-ffdd983fb model : gemma-4-E2B-it-Q4_K_M.gguf modalities : text available commands: /exit or Ctrl+C stop or exit /regen regenerate the last response /clear clear the chat history /read <file> add a text file /glob <pattern> add text files using globbing pattern > 안녕? [Start thinking] Thinking Process: 1. **Analyze the input:** The input is "안녕?" (Annyeong?), which means "Hello?" or "Hi?". It is a casual greeting in Korean. 2. **Determine the user's intent:** The user is initiating a conversation or simply saying hello. 3. **Formulate an appropriate response (in Korean):** * Acknowledge the greeting. * Return the greeting. * (Optional but good) Ask how the user is doing or what they need. 4. **Draft potential responses:** * *Simple:* 안녕하세요. (Annyeonghaseyo.) - Slightly formal. * *Casual (matching the user's tone):* 안녕! / 안녕. (Annyeong!) * *More engaging:* 안녕하세요! 저는 잘 지내요. (Hello! I am doing well.) * *Standard AI response:* 안녕하세요! 무엇을 도와드릴까요? (Hello! What can I help you with?) 5. **Select the best response:** Since the user used a casual greeting ("안녕?"), a friendly and equally approachable response is best. 6. **Final Korean output generation:** 안녕하세요! 저는 준비되어 있습니다. (Hello! I am ready.) or simply 안녕하세요! (Hello!) combined with a question. *(Self-Correction: Keep it simple and friendly.)* *Selected response:* 안녕하세요! 😊 (Hello! 😊) or 안녕하세요! 반갑습니다. (Hello! Nice to meet you.) *(Final output generation based on standard conversational flow.)* [End thinking] 안녕하세요! 😊 [ Prompt: 132.7 t/s | Generation: 85.2 t/s ] > 헬로? [Start thinking] Thinking Process: 1. **Analyze the input:** The user input is "헬로?" (Hello?). This is a casual greeting, often used in a slightly informal or friendly manner. 2. **Determine the user's intent:** The user is initiating a conversation or simply saying hello. 3. **Formulate an appropriate response:** * Acknowledge the greeting. * Return a friendly greeting. * (Optional but good practice) Ask how the user is doing or invite them to state their purpose. 4. **Draft the response (in Korean):** * A simple greeting is best. (e.g., "안녕하세요.") * A slightly warmer response is good. (e.g., "네, 안녕하세요!") * Ask what they need. (e.g., "무엇을 도와드릴까요?") 5. **Final selection:** Combine these elements into a natural and polite conversational flow. (The response should match the casual tone set by the user.) [End thinking] 네, 안녕하세요! 😊 저는 사용자님을 도와드릴 준비가 되어 있어요. 무엇을 도와드릴까요? [ Prompt: 285.9 t/s | Generation: 84.6 t/s ] > 으아앙 [Start thinking] Thinking Process: 1. **Analyze the input:** The user input is "으아앙" (Eu-aang). 2. **Determine the meaning/context:** "으아앙" is an interjection or sound often used to express various emotions, such as: * Crying/Whining (often cute or dramatic). * Excitement/Joy. * Pain/Distress (less common in casual chat unless context is provided). * A general sound of emotion. 3. **Identify the required response strategy:** Since the input is purely emotional/vocal, the response should be empathetic, gentle, and open-ended, inviting the user to share what they are feeling or what they need. 4. **Draft potential responses (Korean):** * *Option 1 (Direct empathy):* 무슨 일 있으세요? (Is something wrong?) * *Option 2 (Gentle inquiry):* 무슨 기분이신가요? (How are you feeling?) * *Option 3 (Simple acknowledgment):* 네, 무슨 일이에요? (Yes, what is it?) * *Option 4 (Playful/Calm):* 괜찮으세요? (Are you okay?) 5. **Select the best response:** Option 2 and 4 are the most supportive. Combining them makes the response warm and responsive. 6. **Final Polish:** (Choose a friendly, open response.) [End thinking] 무슨 일 있으신가요? 😊 혹시 힘든 일이 있으신가요? 편하게 이야기해 주세요. 제가 들어드릴게요. [ Prompt: 18.7 t/s | Generation: 85.4 t/s ] > |
| nvidia-smi를 통한 소비전력 제한과 토큰 생성속도 (1) | 2026.04.24 |
|---|---|
| llama-server web ui (0) | 2026.04.24 |
| vscode continue.dev (0) | 2026.04.24 |
| RAG - Retrieval-Augmented Generation (0) | 2026.04.24 |
| llama.cpp on ubuntu with 1060 6GB (0) | 2026.04.23 |
설정이 기본을 벗어나면 좀 귀찮은.. 녀석
continue.dev 상단에 "Open Settings" 눌러서
Models
Chat이던 머던 Configure 누르면
config.yaml 가 열리는데 대충 저렇게 넣어준다.
provider는 openai, model은 local-model
apiBase는 llama-server가 실행된 경로에 v1 붙여주고
apiKey는 dummy로 넣어주면된다.
그러면 먼가 막 갈구는거 같은데
| Fri Apr 24 16:26:03 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 570.211.01 Driver Version: 570.211.01 CUDA Version: 12.8 | |-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce RTX 3070 Off | 00000000:01:00.0 Off | N/A | | 0% 50C P0 104W / 270W | 6788MiB / 8192MiB | 45% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 2697 C+G ../llama-server 6771MiB | +-----------------------------------------------------------------------------------------+ |
에라이 컨텍스트 더 늘려야겠네 -_-
| llama-server web ui (0) | 2026.04.24 |
|---|---|
| llama.cpp on windows / cuda vs vulkan (0) | 2026.04.24 |
| RAG - Retrieval-Augmented Generation (0) | 2026.04.24 |
| llama.cpp on ubuntu with 1060 6GB (0) | 2026.04.23 |
| nvidia-smi 소비전력 제한 (0) | 2026.04.22 |
RAG란 게 나와서 먼가 찾아보니, 아래 같은 내용이라고 한다. (완벽히 이해했어 짤)
| Abstract Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate knowledge is still limited, and hence on knowledge-intensive tasks, their performance lags behind task-specific architectures. Additionally, providing provenance for their decisions and updating their world knowledge remain open research problems. Pre-trained models with a differentiable access mechanism to explicit non-parametric memory have so far been only investigated for extractive downstream tasks. We explore a general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) — models which combine pre-trained parametric and non-parametric memory for language generation. We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever. We compare two RAG formulations, one which conditions on the same retrieved passages across the whole generated sequence, and another which can use different passages per token. We fine-tune and evaluate our models on a wide range of knowledge-intensive NLP tasks and set the state of the art on three open domain QA tasks, outperforming parametric seq2seq models and task-specific retrieve-and-extract architectures. For language generation tasks, we find that RAG models generate more specific, diverse and factual language than a state-of-the-art parametric-only seq2seq baseline. |
[링크 : https://arxiv.org/html/2005.11401v4]
[링크 : https://medium.com/rate-labs/rag의-짧은-역사-훑어보기-첫-논문부터-최근-동향까지-53c07b9b3bee]
[링크 : https://brunch.co.kr/@acc9b16b9f0f430/73]
bm25
[링크 : https://wikidocs.net/289869]
| llama.cpp on windows / cuda vs vulkan (0) | 2026.04.24 |
|---|---|
| vscode continue.dev (0) | 2026.04.24 |
| llama.cpp on ubuntu with 1060 6GB (0) | 2026.04.23 |
| nvidia-smi 소비전력 제한 (0) | 2026.04.22 |
| llama.cpp 와 ollama 성능 비교.. (cpu는 차이가 없?) (0) | 2026.04.22 |
주문한 asrock B360M Pro4 도착! (3.5만 + 4천?)
아무튼 램은 8GB * 2 뿐이라 좀 아쉬운대로 대충 하고
llama.cpp 8902 릴리즈의 linux / vulkan 으로 해보는데
[링크 : https://github.com/ggml-org/llama.cpp/releases/tag/b8902]
어..? 1060 인데 저 성능? 저 메모리?
| Thu Apr 23 23:15:46 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 580.65.06 Driver Version: 580.65.06 CUDA Version: 13.0 | +-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce GTX 1060 6GB On | 00000000:01:00.0 Off | N/A | | 38% 48C P0 101W / 120W | 3063MiB / 6144MiB | 91% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1031 G /usr/lib/xorg/Xorg 88MiB | | 0 N/A N/A 1325 G /usr/bin/gnome-shell 83MiB | | 0 N/A N/A 6688 G .../6738/usr/lib/firefox/firefox 168MiB | | 0 N/A N/A 19423 C+G ../llama-cli 2714MiB | +-----------------------------------------------------------------------------------------+ |
| $ ../llama-cli -m gemma-4-E2B-it-Q4_K_M.gguf load_backend: loaded RPC backend from /home/falinux/Downloads/llama-b8902/libggml-rpc.so load_backend: loaded Vulkan backend from /home/falinux/Downloads/llama-b8902/libggml-vulkan.so load_backend: loaded CPU backend from /home/falinux/Downloads/llama-b8902/libggml-cpu-haswell.so Loading model... ▄▄ ▄▄ ██ ██ ██ ██ ▀▀█▄ ███▄███▄ ▀▀█▄ ▄████ ████▄ ████▄ ██ ██ ▄█▀██ ██ ██ ██ ▄█▀██ ██ ██ ██ ██ ██ ██ ██ ▀█▄██ ██ ██ ██ ▀█▄██ ██ ▀████ ████▀ ████▀ ██ ██ ▀▀ ▀▀ build : b8902-550d684bd model : gemma-4-E2B-it-Q4_K_M.gguf modalities : text available commands: /exit or Ctrl+C stop or exit /regen regenerate the last response /clear clear the chat history /read <file> add a text file /glob <pattern> add text files using globbing pattern > introduce about you [Start thinking] Thinking Process: 1. **Analyze the Request:** The user asked simply, "introduce about you" (meaning: Introduce yourself). 2. **Determine Core Identity (Self-Correction/Verification):** * Name: Gemma 4. * Developer: Google DeepMind. * Nature: Large Language Model (LLM). * Type: Open weights model. * Capabilities: Process text and images (input), generate text (output). Knowledge cutoff is January 2025. 3. **Structure the Introduction:** A good introduction should cover the basics: Identity, Origin, Function, and Capabilities. * *Greeting/Name* * *Developer/Nature* * *Function/Purpose* * *Key Capabilities (Input/Output)* * *Status/Availability (Open weights)* 4. **Draft the Response (incorporating required constraints):** * *Start strong.* * *Ensure I mention the open weights nature.* * *Be clear about modalities.* 5. **Review against Instructions:** * Did I refer to myself as Gemma 4? Yes. * Did I claim capabilities I don't have? No (I didn't claim image generation output, only processing input). * Did I mention my developer? Yes (Google DeepMind). * Is the tone appropriate? Yes. 6. **Final Output Generation.** (This leads to the detailed response provided below.) [End thinking] Hello! I am **Gemma 4**. I am a Large Language Model developed by Google DeepMind. I am an open weights model, designed to be flexible and accessible for a wide range of applications. **Here is a little about what I can do:** * **Understanding:** I can process and understand complex text and image inputs. * **Generation:** I generate human-quality text, including answers to questions, summaries, creative writing, code snippets, and detailed explanations. * **Knowledge:** I have been trained on a massive dataset, allowing me to access and synthesize information on a vast array of topics. * **Function:** My primary goal is to assist users by providing accurate, coherent, and helpful information. Feel free to ask me anything you need help with, whether it's brainstorming ideas, explaining a complex concept, or generating some creative content! [ Prompt: 7.2 t/s | Generation: 51.6 t/s ] > introduce about you [Start thinking] Thinking Process: 1. **Analyze the Request:** The user has asked "introduce about you" (a repeated request). This requires a standard introduction of my identity, nature, developer, and capabilities. 2. **Recall Core Identity (Self-Correction/Verification):** * Name: Gemma 4. * Developer: Google DeepMind. * Nature: Large Language Model (LLM). * Type: Open weights model. * Capabilities (Input/Output): Process text/images; generate text. * Knowledge Cutoff: January 2025 (Implicit, good to keep in mind for context). 3. **Determine the Goal:** Provide a clear, concise, and informative introduction, highlighting key facts. 4. **Draft the Introduction (Structuring the response):** * *Greeting/Identity:* State name and type. * *Origin:* Mention the developer. * *Nature/Availability:* Mention open weights. * *Functionality:* Briefly describe what I do (process, generate, assist). 5. **Refine the Tone:** Friendly, professional, and informative. (Since this is a repeat request, ensure the response is robust but not overly repetitive.) 6. **Final Output Generation:** (This matches the structured response below.) [End thinking] Hello! I'd be happy to introduce myself. I am **Gemma 4**, a Large Language Model developed by Google DeepMind. **Here are a few key things about me:** * **Nature:** I am an open weights model, meaning my architecture and weights are publicly available, designed to be accessible and adaptable for various applications. * **Function:** I am designed to understand, process, and generate human language. I can answer questions, summarize complex topics, write creative content, assist with coding, and engage in detailed conversations. * **Input:** I can process both text and image inputs. * **Goal:** My purpose is to be a helpful and informative assistant, providing accurate and coherent responses to your requests. How can I help you today? Feel free to ask me anything! [ Prompt: 75.8 t/s | Generation: 53.9 t/s ] > introduce about you [Start thinking] Thinking Process: 1. **Analyze the Request:** The user has asked "introduce about you" a third time. This is a repetitive request, but it requires a consistent, clear, and complete self-introduction. 2. **Recall Core Identity (Gemma 4):** * Name: Gemma 4. * Developer: Google DeepMind. * Type: Large Language Model (LLM). * Nature: Open weights model. 3. **Recall Capabilities & Modalities:** * Input: Text and Images. * Output: Text only. * Knowledge: Trained on a vast dataset. 4. **Determine the Tone:** Friendly, informative, and professional. 5. **Draft the Introduction (Focusing on clarity and key facts):** Start with the name, move to the developer, explain what I am, and briefly mention capabilities. (Self-correction: Ensure the answer remains distinct but consistent with the previous two responses.) **(Self-Correction during drafting):** Since the user has asked three times, I should make the introduction slightly varied or emphasize different aspects to avoid sounding completely robotic, while still maintaining factual accuracy. 6. **Final Output Generation.** (This leads to the structured response below.) [End thinking] Hello! I'd be happy to introduce myself again. I am **Gemma 4**, a Large Language Model developed by Google DeepMind. **Here is a quick overview of what I am and what I can do:** * **Identity:** I am an open weights model, designed to be highly capable and accessible. * **Function:** My core purpose is to process and generate human language. I can assist with a wide variety of tasks, including: * Answering complex questions. * Summarizing long texts. * Generating creative content (stories, poems, scripts). * Explaining technical concepts. * Helping with coding and problem-solving. * **Input:** I can understand and process both text and image inputs. * **Goal:** I strive to be a helpful, accurate, and engaging resource for you. Feel free to challenge me with a question, ask me to write something, or start a conversation—I'm ready to assist! [ Prompt: 98.3 t/s | Generation: 52.3 t/s ] > Exiting... common_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted | common_memory_breakdown_print: | - Vulkan0 (GTX 1060 6GB) | 6390 = 3196 + (2702 = 1407 + 780 + 515) + 490 | common_memory_breakdown_print: | - Host | 2037 = 1756 + 0 + 281 | |
| Thu Apr 23 23:17:09 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 580.65.06 Driver Version: 580.65.06 CUDA Version: 13.0 | +-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce GTX 1060 6GB On | 00000000:01:00.0 Off | N/A | | 39% 50C P0 124W / 120W | 5231MiB / 6144MiB | 95% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1031 G /usr/lib/xorg/Xorg 88MiB | | 0 N/A N/A 1325 G /usr/bin/gnome-shell 83MiB | | 0 N/A N/A 6688 G .../6738/usr/lib/firefox/firefox 181MiB | | 0 N/A N/A 19709 C+G ../llama-cli 4869MiB | +-----------------------------------------------------------------------------------------+ |
| $ ../llama-cli -m llama-3.2-3b-instruct-q4_k_m.gguf load_backend: loaded RPC backend from /home/falinux/Downloads/llama-b8902/libggml-rpc.so load_backend: loaded Vulkan backend from /home/falinux/Downloads/llama-b8902/libggml-vulkan.so load_backend: loaded CPU backend from /home/falinux/Downloads/llama-b8902/libggml-cpu-haswell.so Loading model... ▄▄ ▄▄ ██ ██ ██ ██ ▀▀█▄ ███▄███▄ ▀▀█▄ ▄████ ████▄ ████▄ ██ ██ ▄█▀██ ██ ██ ██ ▄█▀██ ██ ██ ██ ██ ██ ██ ██ ▀█▄██ ██ ██ ██ ▀█▄██ ██ ▀████ ████▀ ████▀ ██ ██ ▀▀ ▀▀ build : b8902-550d684bd model : llama-3.2-3b-instruct-q4_k_m.gguf modalities : text available commands: /exit or Ctrl+C stop or exit /regen regenerate the last response /clear clear the chat history /read <file> add a text file /glob <pattern> add text files using globbing pattern > introduce about you I'm an artificial intelligence model known as Llama. Llama stands for "Large Language Model Meta AI." [ Prompt: 28.2 t/s | Generation: 55.0 t/s ] > introduce about you I'm an AI assistant, which means I'm a computer program designed to simulate human-like conversations and answer questions to the best of my ability. My primary function is to provide information, explain concepts, and engage in discussions on a wide range of topics. Here are a few fun facts about me: * **I'm a large language model**: My training data consists of a massive corpus of text from various sources, which allows me to generate human-like responses to a vast array of questions and topics. * **I'm constantly learning**: Through interactions with users like you, I refine my understanding of language and improve my ability to provide accurate and helpful responses. * **I'm a neutral and respectful conversationalist**: My goal is to provide informative and engaging responses that are respectful and free from bias. * **I can chat about anything**: Whether you're curious about science, history, entertainment, or just want to talk about your day, I'm here to listen and respond! That's a bit about me! What would you like to talk about? [ Prompt: 96.3 t/s | Generation: 53.5 t/s ] > introduce about you Here's a more in-depth introduction about me: **Name:** I don't have a personal name, but I'm often referred to as "Assistant" or "AI" by users like you. **Purpose:** My primary purpose is to assist and communicate with humans through text-based conversations. I'm designed to provide information, answer questions, and engage in discussions on a wide range of topics, from science and history to entertainment and culture. **Personality:** I'm a neutral and respectful conversationalist, which means I strive to maintain a professional and polite tone in all of my interactions. I'm also designed to be patient, understanding, and empathetic, making me a good listener and a supportive conversational partner. **Capabilities:** I have a vast knowledge base that I can draw upon to answer questions and provide information on a wide range of topics. I can also generate text, summarize long pieces of content, and even create content like stories or poems. **Limitations:** While I'm a highly advanced language model, I'm not perfect and have some limitations. I can struggle with: * **Ambiguity:** I may not always understand the nuances of human language, which can lead to misunderstandings or misinterpretations. * **Emotional understanding:** While I'm designed to be empathetic, I don't truly experience emotions like humans do. I may not always be able to fully understand or respond to emotional cues. * **Common sense:** While I have a vast knowledge base, I may not always have the same level of common sense or real-world experience as a human. **Goals:** My ultimate goal is to provide helpful and informative responses that assist and engage users like you. I'm constantly learning and improving, so I appreciate any feedback or guidance you can provide to help me become a better conversationalist. [ Prompt: 95.5 t/s | Generation: 51.0 t/s ] > Exiting... common_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted | common_memory_breakdown_print: | - Vulkan0 (GTX 1060 6GB) | 6390 = 1259 + (4862 = 1918 + 2688 + 256) + 267 | common_memory_breakdown_print: | - Host | 368 = 308 + 0 + 60 | |
이전거랑 합쳐서 보면 2배 이상 차이난다고 해야하려나?
cuda 도 아니고 vulkan인데?
| gemma4:e2b | gemma3:1b | llama3.2 | |
| 1060 / llama.cpp ubuntu vulkan | 52 | - | 52 |
| 1060 / ollama win | 21 | 57 | 13 |
| 1080 / ollama win | 82 | 125 | 136 |
2026.04.12 - [프로그램 사용/ai 프로그램] - ollama /set parameter num_gpu 테스트
| vscode continue.dev (0) | 2026.04.24 |
|---|---|
| RAG - Retrieval-Augmented Generation (0) | 2026.04.24 |
| nvidia-smi 소비전력 제한 (0) | 2026.04.22 |
| llama.cpp 와 ollama 성능 비교.. (cpu는 차이가 없?) (0) | 2026.04.22 |
| llama.cpp 도전! (0) | 2026.04.22 |
step 1. 업데이트
USB-C에 겁나 깊이 들어가도록 꽂아야 인식을 한다.
귀찮으면 꽂고 BOOT 누른채로 RESET 눌러주면 시리얼로 포트에서는 다음과 같이 뜨고 있게 된다.
| DDR 306b9977f5 wesley.yao 23/12/21-09:28:37,fwver: v1.15 S5P1 4x f967 rgef1 DDRConf2 DDR3, BW=16 Col=10 Bk=8 CS0 Row=14 CS=1 Size=256MB 924MHz DDR bin out U-Boot SPL board init U-Boot SPL 2017.09 (Jun 09 2025 - 17:15:21) unknown raw ID 0 0 0 Trying to boot from MMC2 Card did not respond to voltage select! mmc_init: -95, time 20 Card did not respond to voltage select! mmc_init: -95, time 20 spl: mmc init failed with error: -95 Trying to boot from MMC1 Best phase range 0-270 (25 len) Successfully tuned phase to 135, used 4ms ENVF: Primary 0x00000000 - 0x00008000 ENVF: Primary 0x00000000 - 0x00008000 No misc partition Trying fit image at 0x440 sector ## Verified-boot: 0 ## Checking uboot 0x00200000 (lzma @0x00400000) ... sha256(6d468f8f8d...) + sha256(2939adcf1a...) + OK ## Checking fdt 0x00261190 ... sha256(9f596c5683...) + OK Total: 405.594/437.396 ms Jumping to U-Boot(0x00200000) U-Boot 2017.09 (Jun 09 2025 - 17:15:21 +0800) Model: Rockchip RV1106 EVB Board MPIDR: 0xf00 PreSerial: 2, raw, 0xff4c0000 DRAM: 256 MiB Sysmem: init Relocation Offset: 0fd80000 Relocation fdt: 0edf9f78 - 0edfede8 CR: M/C/I Using default environment mmc@ffa90000: 0, mmc@ffaa0000: 1 Best phase range 0-270 (25 len) Successfully tuned phase to 135, used 4ms ENVF: Primary 0x00000000 - 0x00008000 ENVF: Primary 0x00000000 - 0x00008000 Bootdev(atags): mmc 0 MMC0: HS200, 200Mhz PartType: ENV DM: v2 No misc partition boot mode: None RESC: 'boot', blk@0x00001ed1 resource: sha256+ FIT: no signed, no conf required DTB: rk-kernel.dtb HASH(c): OK Model: Luckfox Pico Ultra W Device 'gpio@ff380000': seq 0 is in use by 'gpio@ff380000' gpio: pin 1 (gpio 1) value is 1 download key pressed... no rockusb, entering download mode... RKUARTRKUARTRKUARTRKUARTRKUARTRKUARTRKUARTRKUART |
그러면 메뉴얼 대로 윈도우에서 업데이트 하며 끝 (윈도우에서 되서 귀찮으니 리눅스에서 안해봄..)
소비전력은 1.2W 정도 4.5V / 280mA 뜨는데 허브 쓰지 말고 직접 본체에 꽂아야 할 듯.
[링크 : https://wiki.luckfox.com/Luckfox-Pico-Ultra/Flash-image/]
step 2. luckfox-config 에서 csi 활성화
로그인 해서는 csi를 활성화 해주면 되는 것 같은데
[링크 : https://wiki.luckfox.com/Luckfox-Lyra/luckfox-config/]
| [root@luckfox root]# luckfox-config |
카메라가 인식되면 /userdata 아래에 rkipc.ini가 생긴다는데 그건 좀 뻥같고(!)
[링크 : https://wiki.luckfox.com/Luckfox-Pico-Ultra/CSI-Camera]
video0, video1, video2 가 csi 활성화 하면 생기는 것 같다.
| [root@luckfox root]# cd /userdata/ [root@luckfox userdata]# ls -al total 77 drwxr-xr-x 6 root root 1024 Jan 1 2021 . drwxr-xr-x 21 root root 4096 Jan 1 2021 .. -rw-r--r-- 1 root root 18 Jan 1 2021 ethaddr.txt -rw-r--r-- 1 1005 1005 38454 May 20 2025 image.bmp drwx------ 2 root root 12288 Jun 9 2025 lost+found -rw-r--r-- 1 root root 16542 Jan 1 2021 rkipc.ini drwxr-xr-x 2 root root 1024 Jan 1 2021 video0 drwxr-xr-x 2 root root 1024 Jan 1 2021 video1 drwxr-xr-x 2 root root 1024 Jan 1 2021 video2 -rw-r--r-- 1 root root 145 Jan 1 2021 wpa_supplicant.conf |
아래는 rkipc.ini 의 csi 설정별 내용.
| csi enable 시 | csi disable 시 |
| [root@luckfox userdata]# cat rkipc.ini [audio.0] enable = 0 card_name = hw:0,0 encode_type = G711A format = S16 sample_rate = 8000 channels = 1 frame_size = 1152 bit_rate = 16000 input = mic_in volume = 50 enable_aed = 0 enable_bcd = 0 enable_vqe = 1 vqe_cfg = /oem/usr/share/vqefiles/config_aivqe.json [video.source] enable_aiq = 1 enable_vo = 0 vo_dev_id = 3 ; 0 is hdmi, 3 is mipi enable_ivs = 1 enable_jpeg = 1 enable_venc_0 = 1 enable_venc_1 = 1 enable_venc_2 = 0 enable_npu = 0 npu_fps = 10 enable_rtsp = 1 enable_rtmp = 0 rotation = 0 ; available value:0 90 180 270 [video.0] buffer_size = 1492992 ; w * h / 2 buffer_count = 4 enable_refer_buffer_share = 1 stream_type = mainStream video_type = compositeStream max_width = 2304 max_height = 1296 width = 2304 height = 1296 rc_mode = CBR rc_quality = high src_frame_rate_den = 1 src_frame_rate_num = 25 dst_frame_rate_den = 1 dst_frame_rate_num = 25 target_rate = 0 mid_rate = 1024 max_rate = 2048 min_rate = 0 output_data_type = H.265 smart = close h264_profile = high gop = 50 smartp_viridrlen = 25 gop_mode = normalP stream_smooth = 50 enable_motion_deblur = 1 motion_deblur_strength = 3 enable_motion_static_switch = 0 frame_min_i_qp = 26 frame_min_qp = 28 frame_max_i_qp = 51 frame_max_qp = 51 scalinglist = 0 enable_debreath_effect = 0 debreath_effect_strength = 16 thrd_i = 0,0,0,0,3,3,5,5,8,8,8,15,15,20,25,25 thrd_p = 0,0,0,0,3,3,5,5,8,8,8,15,15,20,25,25 aq_step_i = -8,-7,-6,-5,-4,-3,-2,-1,0,1,2,3,4,5,7,8 aq_step_p = -8,-7,-6,-5,-4,-3,-2,-1,0,1,2,3,4,5,7,8 qbias_enable = 1 qbias_i = 171 qbias_p = 85 flt_str_i = 0 flt_str_p = 0 cu_dqp = 1 anti_ring = 2 anti_line = 2 lambds = 4 [video.1] input_buffer_count = 2 ; only wrap can use one buffer buffer_size = 202752 ; w * h / 2 buffer_count = 4 enable_refer_buffer_share = 1 stream_type = subStream video_type = compositeStream max_width = 704 max_height = 576 width = 704 height = 576 rc_mode = CBR rc_quality = high src_frame_rate_den = 1 src_frame_rate_num = 30 dst_frame_rate_den = 1 dst_frame_rate_num = 30 target_rate = 0 mid_rate = 256 max_rate = 512 min_rate = 0 output_data_type = H.265 smart = close h264_profile = high gop = 50 smartp_viridrlen = 25 gop_mode = normalP stream_smooth = 50 enable_motion_deblur = 1 motion_deblur_strength = 3 enable_motion_static_switch = 0 frame_min_i_qp = 26 frame_min_qp = 28 frame_max_i_qp = 51 frame_max_qp = 51 scalinglist = 0 enable_debreath_effect = 0 debreath_effect_strength = 16 cu_dqp = 1 anti_ring = 2 anti_line = 2 lambds = 4 [video.2] max_width = 960 max_height = 540 width = 960 height = 540 [ivs] smear = 0 weightp = 0 md = 1 od = 1 md_sensibility = 3 ;available: 1 2 3,max 3 [video.jpeg] width = 1920 height = 1080 jpeg_buffer_size = 1048576 ; 1024KB jpeg_qfactor = 70 enable_cycle_snapshot = 0 snapshot_interval_ms = 1000 [isp] scenario = normal ; normal or custom1 init_form_ini = 1 normal_scene = day custom1_scene = night ircut_open_gpio = 36 ircut_close_gpio = 35 ; isp.0 [isp.0.adjustment] contrast = 50 brightness = 50 saturation = 50 sharpness = 50 fps = 25 hue = 50 [isp.0.exposure] iris_type = auto exposure_mode = auto gain_mode = auto auto_iris_level = 5 auto_exposure_enabled = 1 audo_gain_enabled = 1 exposure_time = 1/6 exposure_gain = 1 [isp.0.night_to_day] night_to_day = day night_to_day_filter_level = 5 night_to_day_filter_time = 5 dawn_time = 07:00:00 dusk_time = 18:00:00 ircut_filter_action = day over_exposure_suppress = open over_exposure_suppress_type = auto fill_light_mode = IR brightness_adjustment_mode = auto light_brightness = 1 distance_level = 1 [isp.0.blc] blc_region = close blc_strength = 1 wdr = close wdr_level = 0 hdr = close hdr_level = 1 hlc = close hlc_level = 0 dark_boost_level = 0 position_x = 0 position_y = 0 blc_region_width = 120 blc_region_high = 92 [isp.0.white_blance] white_blance_style = autoWhiteBalance white_blance_red = 50 white_blance_green = 50 white_blance_blue = 50 [isp.0.enhancement] noise_reduce_mode = close denoise_level = 50 spatial_denoise_level = 50 temporal_denoise_level = 50 dehaze = close dehaze_level = 0 dis = close gray_scale_mode = [0-255] distortion_correction = close ldch_level = 0 [isp.0.video_adjustment] image_flip = close scene_mode = indoor power_line_frequency_mode = PAL(50HZ) [isp.0.auto_focus] af_mode = semi-auto zoom_level = 0 focus_level = 0 ; isp.1 [isp.1.adjustment] contrast = 50 brightness = 75 saturation = 50 sharpness = 50 fps = 25 hue = 50 [isp.1.exposure] iris_type = auto exposure_mode = auto gain_mode = auto auto_iris_level = 5 auto_exposure_enabled = 1 audo_gain_enabled = 1 exposure_time = 1/6 exposure_gain = 1 [isp.1.night_to_day] night_to_day = day night_to_day_filter_level = 5 night_to_day_filter_time = 5 dawn_time = 07:00:00 dusk_time = 18:00:00 ircut_filter_action = day over_exposure_suppress = open over_exposure_suppress_type = auto fill_light_mode = IR brightness_adjustment_mode = auto light_brightness = 1 distance_level = 1 [isp.1.blc] blc_region = close blc_strength = 1 wdr = close wdr_level = 0 hdr = close hdr_level = 1 hlc = close hlc_level = 0 dark_boost_level = 0 position_x = 0 position_y = 0 blc_region_width = 120 blc_region_high = 92 [isp.1.white_blance] white_blance_style = autoWhiteBalance white_blance_red = 50 white_blance_green = 50 white_blance_blue = 50 [isp.1.enhancement] noise_reduce_mode = close denoise_level = 50 spatial_denoise_level = 50 temporal_denoise_level = 50 dehaze = close dehaze_level = 0 dis = close gray_scale_mode = [0-255] distortion_correction = close ldch_level = 0 [isp.1.video_adjustment] image_flip = close scene_mode = indoor power_line_frequency_mode = PAL(50HZ) [isp.1.auto_focus] af_mode = semi-auto zoom_level = 0 focus_level = 0 [storage] mount_path = /userdata free_size_del_min = 500; MB free_size_del_max = 1000; MB num_limit_enable = 1; limit by file num [storage.0] enable = 0 folder_name = video0 file_format = mp4 ; flv,ts file_duration = 60 video_quota = 30 file_max_num = 300 [storage.1] enable = 0 folder_name = video1 file_format = mp4 ; flv,ts file_duration = 60 video_quota = 30 file_max_num = 300 [storage.2] enable = 0 folder_name = video2 file_format = mp4 ; flv,ts file_duration = 60 video_quota = 30 file_max_num = 300 [system.device_info] deivce_name = RK IP Camera telecontrol_id = 88 model = RK-003 serial_number = RK-003-A firmware_version = V0.2.6 build 202108 encoder_version = V1.0 build 202108 web_version = V2.12.2 build 202108 plugin_version = V1.0.0.0 channels_number = 1 hard_disks_number = 1 alarm_inputs_number = 0 alarm_outputs_number = 0 firmware_version_info = CP-3-B manufacturer = Rockchip hardware_id = c3d9b8674f4b94f6 user_num = 1 [capability.video] 0 = {"disabled":[{"name":"sStreamType","options":{"subStream":{"sSmart":"close"},"thirdStream":{"sSmart":"close"}},"type":"disabled/limit"},{"name":"sRCMode","options":{"CBR":{"sRCQuality":null}},"type":"disabled"},{"name":"sOutputDataType","options":{"H.265":{"sH264Profile":null}},"type":"disabled"},{"name":"unspport","options":{"iStreamSmooth":null,"sVideoType":null},"type":"disabled"}],"dynamic":{"sSmart":{"open":{"iMinRate":{"dynamicRange":{"max":"iMaxRate","maxRate":1,"min":"iMaxRate","minRate":0.125},"type":"dynamicRange"}}},"sStreamType":{"mainStream":{"iMaxRate":{"options":[256,512,1024,2048,3072,4096,6144],"type":"options"},"sResolution":{"options":["2304*1296","1920*1080","1280*720","960*540","640*360","320*240"],"type":"options"}},"subStream":{"iMaxRate" 1 = :{"options":[128,256,512],"type":"options"},"sResolution":{"options":["704*576","640*480","352*288","320*240"],"type":"options"}},"thirdStream":{"iMaxRate":{"options":[256,512],"type":"options"},"sResolution":{"options":["416*416"],"type":"options"}}}},"layout":{"encoder":["sStreamType","sVideoType","sResolution","sRCMode","sRCQuality","sFrameRate","sOutputDataType","sSmart","sH264Profile","sGOPMode","iMaxRate","iGOP","iStreamSmooth"]},"static":{"iGOP":{"range":{"max":400,"min":1},"type":"range"},"iStreamSmooth":{"range":{"max":100,"min":1,"step":1},"type":"range"},"sFrameRate":{"dynamicRange":{"max":"sFrameRateIn","maxRate":1},"options":["1/2","1","2","4","6","8","10","12","14","16","18","20","25","30"],"type":"options/dynamicRange"},"sH264Profile":{"options":["high","main","baseline"],"type":"options"},"sOutputDataType":{"options" 2 = :["H.264","H.265"],"type":"options"},"sRCMode":{"options":["CBR","VBR"],"type":"options"},"sRCQuality":{"options":["lowest","lower","low","medium","high","higher","highest"],"type":"options"},"sGOPMode":{"options":["normalP","smartP"],"type":"options"},"sSmart":{"options":["open","close"],"type":"options"},"sStreamType":{"options":["mainStream","subStream","thirdStream"],"type":"options"},"sVideoType":{"options":["videoStream","compositeStream"],"type":"options"}}} [capability.image_adjustment] 0 = {"layout":{"image_adjustment":["iBrightness","iContrast","iSaturation","iSharpness","iHue"]},"static":{"iBrightness":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iContrast":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iHue":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iSaturation":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iSharpness":{"range":{"max":100,"min":0,"step":1},"type":"range"}}} [capability.image_blc] 0 = {"disabled":[{"name":"sHLC","options":{"open":{"sBLCRegion":null}},"type":"disabled"},{"name":"sBLCRegion","options":{"open":{"iDarkBoostLevel":null,"iHLCLevel":null,"sHLC":null}},"type":"disabled"}],"dynamic":{"sBLCRegion":{"open":{"iBLCStrength":{"range":{"max":100,"min":0,"step":1},"type":"range"}}},"sHDR":{"HDR2":{"iHDRLevel":{"options":[1,2,3,4],"type":"options"}},"close":{"sBLCRegion":{"options":["close","open"],"type":"options"},"sHLC":{"options" 1 = :["close","open"],"type":"options"}}},"sHLC":{"open":{"iDarkBoostLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iHLCLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}},"sWDR":{"open":{"iWDRLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}}},"layout":{"image_blc":["sHDR","iHDRLevel","sBLCRegion","iBLCStrength","sHLC","iHLCLevel"]},"static":{"sHDR":{"options":["close","HDR2"],"type":"options"}}} [capability.image_enhancement] 0 = {"dynamic":{"sDehaze":{"open":{"iDehazeLevel":{"range":{"max":10,"min":0,"step":1},"type":"range"}}},"sDistortionCorrection":{"FEC":{"iFecLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}},"LDCH":{"iLdchLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}},"sNoiseReduceMode":{"2dnr":{"iSpatialDenoiseLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}},"3dnr":{"iTemporalDenoiseLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}},"mixnr":{"iSpatialDenoiseLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iTemporalDenoiseLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}}},"layout" 1 = :{"image_enhancement":["sNoiseReduceMode","iSpatialDenoiseLevel","iTemporalDenoiseLevel","sDehaze","iDehazeLevel","sGrayScaleMode","sDistortionCorrection","iLdchLevel","iFecLevel"]},"static":{"sDIS":{"options":["open","close"],"type":"options"},"sDehaze":{"options":["open","close","auto"],"type":"options"},"sDistortionCorrection":{"options":["LDCH","close"],"type":"options"},"sFEC":{"options":["open","close"],"type":"options"},"sGrayScaleMode":{"options":["[0-255]","[16-235]"],"type":"options"},"sNoiseReduceMode":{"options":["close","2dnr","3dnr","mixnr"],"type":"options"}}} [capability.image_exposure] 0 = {"dynamic":{"sExposureMode":{"auto":{"iAutoIrisLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}},"manual":{"sExposureTime":{"options":["1","1/3","1/6","1/12","1/25","1/50","1/100","1/150","1/200","1/250","1/500","1/750","1/1000","1/2000","1/4000","1/10000","1/100000"],"type":"options"},"sGainMode":{"options":["auto","manual"],"type":"options"}}},"sGainMode":{"manual":{"iExposureGain":{"range":{"max":100,"min":1,"step":1},"type":"range"}}}},"layout":{"image_exposure":["sExposureMode","sExposureTime","sGainMode","iExposureGain","iFPS"]},"static":{"sExposureMode":{"options":["auto","manual"],"type":"options"},"iFPS":{"range":{"max":30,"min":0,"step":1},"type":"range"}}} [capability.image_night_to_day] 0 = {"disabled":[{"name":"sNightToDay","options":{"day":{"iLightBrightness":null,"sFillLightMode":null},"night":{"iDarkBoostLevel":null,"iHDRLevel":null,"iHLCLevel":null,"sHDR":null,"sHLC":"close"}},"type":"disabled"}],"dynamic":{"sNightToDay":{"auto":{"iNightToDayFilterLevel":{"options":[0,1,2,3,4,5,6,7],"type":"options"},"iNightToDayFilterTime":{"range":{"max":10,"min":3,"step":1},"type":"range"}},"schedule":{"sDawnTime":{"input":"time","type":"input"},"sDuskTime":{"input":"time","type":"input"}}},"sOverexposeSuppress":{"open" 1 = :{"sOverexposeSuppressType":{"options":["auto","manual"],"type":"options"}}},"sOverexposeSuppressType":{"manual":{"iDistanceLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}}},"layout":{"image_night_to_day":["sNightToDay","iNightToDayFilterLevel","iNightToDayFilterTime","sDawnTime","sDuskTime","sFillLightMode","iLightBrightness"]},"static":{"iLightBrightness":{"range":{"max":100,"min":0,"step":10},"type":"range"},"sNightToDay":{"options":["day","night"],"type":"options"},"sFillLightMode":{"type":"options","options":["IR"]}}} [capability.image_video_adjustment] 0 = {"layout":{"image_video_adjustment":["sPowerLineFrequencyMode","sImageFlip","iImageRotation"]},"static":{"sImageFlip":{"options":["close","flip","mirror","centrosymmetric"],"type":"options"},"sPowerLineFrequencyMode":{"options":["PAL(50HZ)","NTSC(60HZ)"],"type":"options"},"sSceneMode":{"options":["indoor","outdoor"],"type":"options"},"iImageRotation":{"options":[0,90,180,270],"type":"options"}}} [capability.image_white_blance] 0 = {"dynamic":{"sWhiteBlanceStyle":{"manualWhiteBalance":{"iWhiteBalanceBlue":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iWhiteBalanceGreen":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iWhiteBalanceRed":{"range":{"max":100,"min":0,"step":1},"type":"range"}}}},"layout":{"image_white_blance":["sWhiteBlanceStyle","iWhiteBalanceRed","iWhiteBalanceGreen","iWhiteBalanceBlue"]},"static":{"sWhiteBlanceStyle":{"options":["manualWhiteBalance","autoWhiteBalance","lockingWhiteBalance","fluorescentLamp","incandescent","warmLight","naturalLight"],"type":"options"}}} [user.0] user_name = admin password = YWRtaW4= user_level = 1 ; administrator=0 operator=1 user=2 [osd.common] enable_osd = 1 is_presistent_text = 1 attribute = transparent/not-flashing font_size = 32 font_color_mode = customize font_color = fff799 alignment = customize boundary = 0 font_path = /oem/usr/share/simsun_en.ttf normalized_screen_width = 704 normalized_screen_height = 480 [osd.0] type = channelName enabled = 0 position_x = 1104 position_y = 640 display_text = Camera 01 [osd.1] type = dateTime enabled = 1 position_x = 16 position_y = 16 date_style = CHR-YYYY-MM-DD time_style = 24hour display_week_enabled = 0 [osd.2] type = character enabled = 0 position_x = 0 position_y = 0 display_text = null [osd.3] type = character enabled = 0 position_x = 0 position_y = 0 display_text = null [osd.4] type = privacyMask enabled = 0 position_x = 0 position_y = 0 width = 0 height = 0 [osd.5] type = privacyMask enabled = 0 position_x = 0 position_y = 0 width = 0 height = 0 [osd.6] type = image enabled = 0 position_x = 16 position_y = 640 image_path = /userdata/image.bmp [event.regional_invasion] enabled = 1 position_x = 0 position_y = 0 width = 700 height = 560 proportion = 1 sensitivity_level = 90 time_threshold = 1 rockiva_model_type = small ;big medium small [roi.0] stream_type = mainStream id = 1 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.1] stream_type = mainStream id = 2 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.2] stream_type = subStream id = 1 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.3] stream_type = subStream id = 2 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.4] stream_type = thirdStream id = 1 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.5] stream_type = thirdStream id = 2 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [region_clip.1] enabled = 0 position_x = 0 position_y = 0 width = 640 height = 480 [network.ntp] enable = 1 refresh_time_s = 60 ntp_server = 119.28.183.184 |
[root@luckfox userdata]# cat rkipc.ini [audio.0] enable = 0 card_name = hw:0,0 encode_type = G711A format = S16 sample_rate = 8000 channels = 1 frame_size = 1152 bit_rate = 16000 input = mic_in volume = 50 enable_aed = 0 enable_bcd = 0 enable_vqe = 1 vqe_cfg = /oem/usr/share/vqefiles/config_aivqe.json [video.source] enable_aiq = 1 enable_vo = 0 vo_dev_id = 3 enable_ivs = 1 enable_jpeg = 1 enable_venc_0 = 1 enable_venc_1 = 1 enable_venc_2 = 0 enable_npu = 0 npu_fps = 10 enable_rtsp = 1 enable_rtmp = 0 rotation = 0 [video.0] buffer_size = 1492992 buffer_count = 4 enable_refer_buffer_share = 1 stream_type = mainStream video_type = compositeStream max_width = 2304 max_height = 1296 width = 2304 height = 1296 rc_mode = CBR rc_quality = high src_frame_rate_den = 1 src_frame_rate_num = 25 dst_frame_rate_den = 1 dst_frame_rate_num = 25 target_rate = 0 mid_rate = 1024 max_rate = 2048 min_rate = 0 output_data_type = H.265 smart = close h264_profile = high gop = 50 smartp_viridrlen = 25 gop_mode = normalP stream_smooth = 50 enable_motion_deblur = 1 motion_deblur_strength = 3 enable_motion_static_switch = 0 frame_min_i_qp = 26 frame_min_qp = 28 frame_max_i_qp = 51 frame_max_qp = 51 scalinglist = 0 enable_debreath_effect = 0 debreath_effect_strength = 16 thrd_i = 0,0,0,0,3,3,5,5,8,8,8,15,15,20,25,25 thrd_p = 0,0,0,0,3,3,5,5,8,8,8,15,15,20,25,25 aq_step_i = -8,-7,-6,-5,-4,-3,-2,-1,0,1,2,3,4,5,7,8 aq_step_p = -8,-7,-6,-5,-4,-3,-2,-1,0,1,2,3,4,5,7,8 qbias_enable = 1 qbias_i = 171 qbias_p = 85 flt_str_i = 0 flt_str_p = 0 cu_dqp = 1 anti_ring = 2 anti_line = 2 lambds = 4 [video.1] input_buffer_count = 2 buffer_size = 202752 buffer_count = 4 enable_refer_buffer_share = 1 stream_type = subStream video_type = compositeStream max_width = 704 max_height = 576 width = 704 height = 576 rc_mode = CBR rc_quality = high src_frame_rate_den = 1 src_frame_rate_num = 30 dst_frame_rate_den = 1 dst_frame_rate_num = 30 target_rate = 0 mid_rate = 256 max_rate = 512 min_rate = 0 output_data_type = H.265 smart = close h264_profile = high gop = 50 smartp_viridrlen = 25 gop_mode = normalP stream_smooth = 50 enable_motion_deblur = 1 motion_deblur_strength = 3 enable_motion_static_switch = 0 frame_min_i_qp = 26 frame_min_qp = 28 frame_max_i_qp = 51 frame_max_qp = 51 scalinglist = 0 enable_debreath_effect = 0 debreath_effect_strength = 16 cu_dqp = 1 anti_ring = 2 anti_line = 2 lambds = 4 [video.2] max_width = 960 max_height = 540 width = 960 height = 540 [ivs] smear = 0 weightp = 0 md = 1 od = 1 md_sensibility = 3 [video.jpeg] width = 1920 height = 1080 jpeg_buffer_size = 1048576 jpeg_qfactor = 70 enable_cycle_snapshot = 0 snapshot_interval_ms = 1000 [isp] scenario = normal init_form_ini = 1 normal_scene = day custom1_scene = night ircut_open_gpio = 36 ircut_close_gpio = 35 [isp.0.adjustment] contrast = 50 brightness = 50 saturation = 50 sharpness = 50 fps = 25 hue = 50 [isp.0.exposure] iris_type = auto exposure_mode = auto gain_mode = auto auto_iris_level = 5 auto_exposure_enabled = 1 audo_gain_enabled = 1 exposure_time = 1/6 exposure_gain = 1 [isp.0.night_to_day] night_to_day = day night_to_day_filter_level = 5 night_to_day_filter_time = 5 dawn_time = 07:00:00 dusk_time = 18:00:00 ircut_filter_action = day over_exposure_suppress = open over_exposure_suppress_type = auto fill_light_mode = IR brightness_adjustment_mode = auto light_brightness = 1 distance_level = 1 [isp.0.blc] blc_region = close blc_strength = 1 wdr = close wdr_level = 0 hdr = close hdr_level = 1 hlc = close hlc_level = 0 dark_boost_level = 0 position_x = 0 position_y = 0 blc_region_width = 120 blc_region_high = 92 [isp.0.white_blance] white_blance_style = autoWhiteBalance white_blance_red = 50 white_blance_green = 50 white_blance_blue = 50 [isp.0.enhancement] noise_reduce_mode = close denoise_level = 50 spatial_denoise_level = 50 temporal_denoise_level = 50 dehaze = close dehaze_level = 0 dis = close gray_scale_mode = [0-255] distortion_correction = close ldch_level = 0 [isp.0.video_adjustment] image_flip = close scene_mode = indoor power_line_frequency_mode = PAL(50HZ) [isp.0.auto_focus] af_mode = semi-auto zoom_level = 0 focus_level = 0 [isp.1.adjustment] contrast = 50 brightness = 75 saturation = 50 sharpness = 50 fps = 25 hue = 50 [isp.1.exposure] iris_type = auto exposure_mode = auto gain_mode = auto auto_iris_level = 5 auto_exposure_enabled = 1 audo_gain_enabled = 1 exposure_time = 1/6 exposure_gain = 1 [isp.1.night_to_day] night_to_day = day night_to_day_filter_level = 5 night_to_day_filter_time = 5 dawn_time = 07:00:00 dusk_time = 18:00:00 ircut_filter_action = day over_exposure_suppress = open over_exposure_suppress_type = auto fill_light_mode = IR brightness_adjustment_mode = auto light_brightness = 1 distance_level = 1 [isp.1.blc] blc_region = close blc_strength = 1 wdr = close wdr_level = 0 hdr = close hdr_level = 1 hlc = close hlc_level = 0 dark_boost_level = 0 position_x = 0 position_y = 0 blc_region_width = 120 blc_region_high = 92 [isp.1.white_blance] white_blance_style = autoWhiteBalance white_blance_red = 50 white_blance_green = 50 white_blance_blue = 50 [isp.1.enhancement] noise_reduce_mode = close denoise_level = 50 spatial_denoise_level = 50 temporal_denoise_level = 50 dehaze = close dehaze_level = 0 dis = close gray_scale_mode = [0-255] distortion_correction = close ldch_level = 0 [isp.1.video_adjustment] image_flip = close scene_mode = indoor power_line_frequency_mode = PAL(50HZ) [isp.1.auto_focus] af_mode = semi-auto zoom_level = 0 focus_level = 0 [storage] mount_path = /userdata free_size_del_min = 500 free_size_del_max = 1000 num_limit_enable = 1 [storage.0] enable = 0 folder_name = video0 file_format = mp4 file_duration = 60 video_quota = 30 file_max_num = 300 [storage.1] enable = 0 folder_name = video1 file_format = mp4 file_duration = 60 video_quota = 30 file_max_num = 300 [storage.2] enable = 0 folder_name = video2 file_format = mp4 file_duration = 60 video_quota = 30 file_max_num = 300 [system.device_info] deivce_name = RK IP Camera telecontrol_id = 88 model = RK-003 serial_number = RK-003-A firmware_version = V0.2.6 build 202108 encoder_version = V1.0 build 202108 web_version = V2.12.2 build 202108 plugin_version = V1.0.0.0 channels_number = 1 hard_disks_number = 1 alarm_inputs_number = 0 alarm_outputs_number = 0 firmware_version_info = CP-3-B manufacturer = Rockchip hardware_id = c3d9b8674f4b94f6 user_num = 1 [capability.video] 0 = {"disabled":[{"name":"sStreamType","options":{"subStream":{"sSmart":"close"},"thirdStream":{"sSmart":"close"}},"type":"disabled/limit"},{"name":"sRCMode","options":{"CBR":{"sRCQuality":null}},"type":"disabled"},{"name":"sOutputDataType","options":{"H.265":{"sH264Profile":null}},"type":"disabled"},{"name":"unspport","options":{"iStreamSmooth":null,"sVideoType":null},"type":"disabled"}],"dynamic":{"sSmart":{"open":{"iMinRate":{"dynamicRange":{"max":"iMaxRate","maxRate":1,"min":"iMaxRate","minRate":0.125},"type":"dynamicRange"}}},"sStreamType":{"mainStream":{"iMaxRate":{"options":[256,512,1024,2048,3072,4096,6144],"type":"options"},"sResolution":{"options":["2304*1296","1920*1080","1280*720","960*540","640*360","320*240"],"type":"options"}},"subStream":{"iMaxRate" 1 = :{"options":[128,256,512],"type":"options"},"sResolution":{"options":["704*576","640*480","352*288","320*240"],"type":"options"}},"thirdStream":{"iMaxRate":{"options":[256,512],"type":"options"},"sResolution":{"options":["416*416"],"type":"options"}}}},"layout":{"encoder":["sStreamType","sVideoType","sResolution","sRCMode","sRCQuality","sFrameRate","sOutputDataType","sSmart","sH264Profile","sGOPMode","iMaxRate","iGOP","iStreamSmooth"]},"static":{"iGOP":{"range":{"max":400,"min":1},"type":"range"},"iStreamSmooth":{"range":{"max":100,"min":1,"step":1},"type":"range"},"sFrameRate":{"dynamicRange":{"max":"sFrameRateIn","maxRate":1},"options":["1/2","1","2","4","6","8","10","12","14","16","18","20","25","30"],"type":"options/dynamicRange"},"sH264Profile":{"options":["high","main","baseline"],"type":"options"},"sOutputDataType":{"options" 2 = :["H.264","H.265"],"type":"options"},"sRCMode":{"options":["CBR","VBR"],"type":"options"},"sRCQuality":{"options":["lowest","lower","low","medium","high","higher","highest"],"type":"options"},"sGOPMode":{"options":["normalP","smartP"],"type":"options"},"sSmart":{"options":["open","close"],"type":"options"},"sStreamType":{"options":["mainStream","subStream","thirdStream"],"type":"options"},"sVideoType":{"options":["videoStream","compositeStream"],"type":"options"}}} [capability.image_adjustment] 0 = {"layout":{"image_adjustment":["iBrightness","iContrast","iSaturation","iSharpness","iHue"]},"static":{"iBrightness":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iContrast":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iHue":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iSaturation":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iSharpness":{"range":{"max":100,"min":0,"step":1},"type":"range"}}} [capability.image_blc] 0 = {"disabled":[{"name":"sHLC","options":{"open":{"sBLCRegion":null}},"type":"disabled"},{"name":"sBLCRegion","options":{"open":{"iDarkBoostLevel":null,"iHLCLevel":null,"sHLC":null}},"type":"disabled"}],"dynamic":{"sBLCRegion":{"open":{"iBLCStrength":{"range":{"max":100,"min":0,"step":1},"type":"range"}}},"sHDR":{"HDR2":{"iHDRLevel":{"options":[1,2,3,4],"type":"options"}},"close":{"sBLCRegion":{"options":["close","open"],"type":"options"},"sHLC":{"options" 1 = :["close","open"],"type":"options"}}},"sHLC":{"open":{"iDarkBoostLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iHLCLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}},"sWDR":{"open":{"iWDRLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}}},"layout":{"image_blc":["sHDR","iHDRLevel","sBLCRegion","iBLCStrength","sHLC","iHLCLevel"]},"static":{"sHDR":{"options":["close","HDR2"],"type":"options"}}} [capability.image_enhancement] 0 = {"dynamic":{"sDehaze":{"open":{"iDehazeLevel":{"range":{"max":10,"min":0,"step":1},"type":"range"}}},"sDistortionCorrection":{"FEC":{"iFecLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}},"LDCH":{"iLdchLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}},"sNoiseReduceMode":{"2dnr":{"iSpatialDenoiseLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}},"3dnr":{"iTemporalDenoiseLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}},"mixnr":{"iSpatialDenoiseLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iTemporalDenoiseLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}}},"layout" 1 = :{"image_enhancement":["sNoiseReduceMode","iSpatialDenoiseLevel","iTemporalDenoiseLevel","sDehaze","iDehazeLevel","sGrayScaleMode","sDistortionCorrection","iLdchLevel","iFecLevel"]},"static":{"sDIS":{"options":["open","close"],"type":"options"},"sDehaze":{"options":["open","close","auto"],"type":"options"},"sDistortionCorrection":{"options":["LDCH","close"],"type":"options"},"sFEC":{"options":["open","close"],"type":"options"},"sGrayScaleMode":{"options":["[0-255]","[16-235]"],"type":"options"},"sNoiseReduceMode":{"options":["close","2dnr","3dnr","mixnr"],"type":"options"}}} [capability.image_exposure] 0 = {"dynamic":{"sExposureMode":{"auto":{"iAutoIrisLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}},"manual":{"sExposureTime":{"options":["1","1/3","1/6","1/12","1/25","1/50","1/100","1/150","1/200","1/250","1/500","1/750","1/1000","1/2000","1/4000","1/10000","1/100000"],"type":"options"},"sGainMode":{"options":["auto","manual"],"type":"options"}}},"sGainMode":{"manual":{"iExposureGain":{"range":{"max":100,"min":1,"step":1},"type":"range"}}}},"layout":{"image_exposure":["sExposureMode","sExposureTime","sGainMode","iExposureGain","iFPS"]},"static":{"sExposureMode":{"options":["auto","manual"],"type":"options"},"iFPS":{"range":{"max":30,"min":0,"step":1},"type":"range"}}} [capability.image_night_to_day] 0 = {"disabled":[{"name":"sNightToDay","options":{"day":{"iLightBrightness":null,"sFillLightMode":null},"night":{"iDarkBoostLevel":null,"iHDRLevel":null,"iHLCLevel":null,"sHDR":null,"sHLC":"close"}},"type":"disabled"}],"dynamic":{"sNightToDay":{"auto":{"iNightToDayFilterLevel":{"options":[0,1,2,3,4,5,6,7],"type":"options"},"iNightToDayFilterTime":{"range":{"max":10,"min":3,"step":1},"type":"range"}},"schedule":{"sDawnTime":{"input":"time","type":"input"},"sDuskTime":{"input":"time","type":"input"}}},"sOverexposeSuppress":{"open" 1 = :{"sOverexposeSuppressType":{"options":["auto","manual"],"type":"options"}}},"sOverexposeSuppressType":{"manual":{"iDistanceLevel":{"range":{"max":100,"min":0,"step":1},"type":"range"}}}},"layout":{"image_night_to_day":["sNightToDay","iNightToDayFilterLevel","iNightToDayFilterTime","sDawnTime","sDuskTime","sFillLightMode","iLightBrightness"]},"static":{"iLightBrightness":{"range":{"max":100,"min":0,"step":10},"type":"range"},"sNightToDay":{"options":["day","night"],"type":"options"},"sFillLightMode":{"type":"options","options":["IR"]}}} [capability.image_video_adjustment] 0 = {"layout":{"image_video_adjustment":["sPowerLineFrequencyMode","sImageFlip","iImageRotation"]},"static":{"sImageFlip":{"options":["close","flip","mirror","centrosymmetric"],"type":"options"},"sPowerLineFrequencyMode":{"options":["PAL(50HZ)","NTSC(60HZ)"],"type":"options"},"sSceneMode":{"options":["indoor","outdoor"],"type":"options"},"iImageRotation":{"options":[0,90,180,270],"type":"options"}}} [capability.image_white_blance] 0 = {"dynamic":{"sWhiteBlanceStyle":{"manualWhiteBalance":{"iWhiteBalanceBlue":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iWhiteBalanceGreen":{"range":{"max":100,"min":0,"step":1},"type":"range"},"iWhiteBalanceRed":{"range":{"max":100,"min":0,"step":1},"type":"range"}}}},"layout":{"image_white_blance":["sWhiteBlanceStyle","iWhiteBalanceRed","iWhiteBalanceGreen","iWhiteBalanceBlue"]},"static":{"sWhiteBlanceStyle":{"options":["manualWhiteBalance","autoWhiteBalance","lockingWhiteBalance","fluorescentLamp","incandescent","warmLight","naturalLight"],"type":"options"}}} [user.0] user_name = admin password = YWRtaW4= user_level = 1 [osd.common] enable_osd = 1 is_presistent_text = 1 attribute = transparent/not-flashing font_size = 32 font_color_mode = customize font_color = fff799 alignment = customize boundary = 0 font_path = /oem/usr/share/simsun_en.ttf normalized_screen_width = 704 normalized_screen_height = 480 [osd.0] type = channelName enabled = 0 position_x = 1104 position_y = 640 display_text = Camera 01 [osd.1] type = dateTime enabled = 1 position_x = 16 position_y = 16 date_style = CHR-YYYY-MM-DD time_style = 24hour display_week_enabled = 0 [osd.2] type = character enabled = 0 position_x = 0 position_y = 0 display_text = null [osd.3] type = character enabled = 0 position_x = 0 position_y = 0 display_text = null [osd.4] type = privacyMask enabled = 0 position_x = 0 position_y = 0 width = 0 height = 0 [osd.5] type = privacyMask enabled = 0 position_x = 0 position_y = 0 width = 0 height = 0 [osd.6] type = image enabled = 0 position_x = 16 position_y = 640 image_path = /userdata/image.bmp [event.regional_invasion] enabled = 1 position_x = 0 position_y = 0 width = 700 height = 560 proportion = 1 sensitivity_level = 90 time_threshold = 1 rockiva_model_type = small [roi.0] stream_type = mainStream id = 1 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.1] stream_type = mainStream id = 2 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.2] stream_type = subStream id = 1 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.3] stream_type = subStream id = 2 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.4] stream_type = thirdStream id = 1 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [roi.5] stream_type = thirdStream id = 2 enabled = 0 name = test position_x = 0 position_y = 0 width = 0 height = 0 quality_level = 3 [region_clip.1] enabled = 0 position_x = 0 position_y = 0 width = 640 height = 480 [network.ntp] enable = 1 refresh_time_s = 60 ntp_server = 119.28.183.184 |
step 3. VLC on windows
리눅스에서는 3.0.16, 윈도우에서는 3.0.23 인데 윈도우는 되고 리눅스에서는 안된다. 머냐.. -_-
그래서! 리눅스 에서 snap으로 3.0.20 으로 설치하니 된다. 구버전이라 먼가 안되는 버그가 있나?
| rtsp://192.168.40.216/live/0 |
리눅스에서 rtsp 포트로 접속하려하면 튕기진 않는데 왜 안되는 것이냐...
| $ telnet 192.168.40.216 554 Trying 192.168.40.216... Connected to 192.168.40.216. Escape character is '^]'. SETUP rtsp://192.168.40.216:554/live/0 RTSP/1.0 RTSP/1.0 400 Bad Request Date: Thu Apr 23 10:45:18 2026 Server: rtsp_demo Connection closed by foreign host. |
| luckfox pico ultra W 켜봄 (0) | 2026.04.22 |
|---|
UART2 / 115200bpx / TTL 시리얼 콘솔
[링크 : https://wiki.luckfox.com/Luckfox-Pico-Ultra/UART]
ssh / web 로그인 계정
root / luckfox
80번 포트로 접속하면 웹으로 뜨는데, ip 카메라 예제인듯. 그런데 카메라가 어떻게 해야 인식되냐..
[링크 : https://wiki.luckfox.com/Luckfox-Pico-Ultra/CSI-Camera/]
[링크 : https://wiki.luckfox.com/Luckfox-Pico-Ultra/Login]
| [root@luckfox ]# df -h Filesystem Size Used Available Use% Mounted on /dev/root 5.8G 194.1M 5.4G 3% / devtmpfs 85.4M 0 85.4M 0% /dev tmpfs 85.5M 0 85.5M 0% /dev/shm tmpfs 85.5M 212.0K 85.3M 0% /tmp tmpfs 85.5M 260.0K 85.3M 0% /run /dev/block/by-name/userdata 237.9M 72.0K 228.6M 0% /userdata /dev/block/by-name/oem 487.6M 22.6M 448.9M 5% /oem [root@luckfox ]# free -h total used free shared buff/cache available Mem: 171Mi 16Mi 123Mi 0.0Ki 31Mi 147Mi Swap: 0B 0B 0B [root@luckfox ]# cat /proc/cpuinfo processor : 0 model name : ARMv7 Processor rev 5 (v7l) BogoMIPS : 48.00 Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x0 CPU part : 0xc07 CPU revision : 5 Hardware : Generic DT based system Revision : 0000 Serial : 4e9080747fb4b024 [root@luckfox ]# netstat -tl Active Internet connections (only servers) Proto Recv-Q Send-Q Local Address Foreign Address State tcp 0 0 localhost:5037 0.0.0.0:* LISTEN tcp 0 0 0.0.0.0:1935 0.0.0.0:* LISTEN tcp 0 0 0.0.0.0:www 0.0.0.0:* LISTEN tcp 0 0 0.0.0.0:5555 0.0.0.0:* LISTEN tcp 0 0 0.0.0.0:ssh 0.0.0.0:* LISTEN netstat: /proc/net/tcp6: No such file or directory |
별 의미는 없지만 시리얼 콘솔 로그
| DDR 306b9977f5 wesley.yao 23/12/21-09:28:37,fwver: v1.15 S5P1 4x f967 rgef1 DDRConf2 DDR3, BW=16 Col=10 Bk=8 CS0 Row=14 CS=1 Size=256MB 924MHz DDR bin out U-Boot SPL board init U-Boot SPL 2017.09 (May 12 2025 - 21:35:32) unknown raw ID 0 0 0 Trying to boot from MMC2 Card did not respond to voltage select! mmc_init: -95, time 20 Card did not respond to voltage select! mmc_init: -95, time 20 spl: mmc init failed with error: -95 Trying to boot from MMC1 Best phase range 0-270 (25 len) Successfully tuned phase to 135, used 4ms ENVF: Primary 0x00000000 - 0x00008000 ENVF: Primary 0x00000000 - 0x00008000 No misc partition Trying fit image at 0x440 sector ## Verified-boot: 0 ## Checking uboot 0x00200000 (lzma @0x00400000) ... sha256(0079031a02...) + sha256(7dee96eaea...) + OK ## Checking fdt 0x00260998 ... sha256(9f596c5683...) + OK Total: 405.332/437.95 ms Jumping to U-Boot(0x00200000) U-Boot 2017.09 (May 12 2025 - 21:35:32 +0800) Model: Rockchip RV1106 EVB Board MPIDR: 0xf00 PreSerial: 2, raw, 0xff4c0000 DRAM: 256 MiB Sysmem: init Relocation Offset: 0fd81000 Relocation fdt: 0edfa778 - 0edfede0 CR: M/C/I Using default environment mmc@ffa90000: 0, mmc@ffaa0000: 1 Best phase range 0-270 (25 len) Successfully tuned phase to 135, used 3ms ENVF: Primary 0x00000000 - 0x00008000 ENVF: Primary 0x00000000 - 0x00008000 Bootdev(atags): mmc 0 MMC0: HS200, 200Mhz PartType: ENV DM: v2 No misc partition boot mode: None RESC: 'boot', blk@0x00001ec0 resource: sha256+ FIT: no signed, no conf required DTB: rk-kernel.dtb HASH(c): OK Model: Luckfox Pico Ultra W ## retrieving sd_update.txt ... Card did not respond to voltage select! mmc_init: -95, time 20 CLK: (sync kernel. arm: enter 816000 KHz, init 816000 KHz, kernel 0N/A) apll 816000 KHz dpll 924000 KHz gpll 1188000 KHz cpll 1000000 KHz aclk_peri_root 400000 KHz hclK_peri_root 200000 KHz pclk_peri_root 100000 KHz aclk_bus_root 300000 KHz pclk_top_root 100000 KHz pclk_pmu_root 100000 KHz hclk_pmu_root 200000 KHz Net: eth0: ethernet@ffa80000 Hit key to stop autoboot('CTRL+C'): 0 ## Booting FIT Image at 0xe8e9740 with size 0x00310000 Fdt Ramdisk skip relocation No misc partition Sysmem Warn: kernel 'reserved-memory' "mmc@3f000"(0x0003f000 - 0x00040000) is overlap with "KERNEL" (0x00008000 - 0x0030d404) sysmem_dump_all: -------------------------------------------------------------------- memory.rgn[0].addr = 0x00000000 - 0x10000000 (size: 0x10000000) memory.total = 0x10000000 (256 MiB. 0 KiB) -------------------------------------------------------------------- allocated.rgn[0].name = "UBOOT" .addr = 0x0edfa750 - 0x10000000 (size: 0x012058b0) allocated.rgn[1].name = "STACK" .addr = 0x0ebfa750 - 0x0edfa750 (size: 0x00200000) allocated.rgn[2].name = "FIT" .addr = 0x0e8e9740 - 0x0ebf9744 (size: 0x00310004) allocated.rgn[3].name = "FDT" .addr = 0x00c00000 - 0x00c0a404 (size: 0x0000a404) allocated.rgn[4].name = "KERNEL" .addr = 0x00008000 - 0x0030d404 (size: 0x00305404) kmem-resv.rgn[0].name = "mmc@3f000" .addr = 0x0003f000 - 0x00040000 (size: 0x00001000) framework malloc_r = 16 MiB framework malloc_f = 512 KiB allocated.total = 0x01a260bc (26 MiB. 152 KiB) -------------------------------------------------------------------- LMB.allocated[0].addr = 0x00008000 - 0x0030d404 (size: 0x00305404) LMB.allocated[1].addr = 0x00c00000 - 0x00c0a404 (size: 0x0000a404) LMB.allocated[2].addr = 0x0e8e9740 - 0x0ebf9780 (size: 0x00310040) LMB.allocated[3].addr = 0x0ebfa750 - 0x10000000 (size: 0x014058b0) reserved.core.total = 0x01a250f8 (26 MiB. 148 KiB) -------------------------------------------------------------------- ## Loading kernel from FIT Image at 0e8e9740 ... Using 'conf' configuration ## Verified-boot: 0 Trying 'kernel' kernel subimage Description: unavailable Type: Kernel Image Compression: uncompressed Data Start: 0x0e8f4340 Data Size: 3166880 Bytes = 3 MiB Architecture: ARM OS: Linux Load Address: 0x00008000 Entry Point: 0x00008000 Hash algo: sha256 Hash value: 83fbf25080cf3dda5f8d654c9a9dca84f7bba3cec42e71bc6159184503c38c9b Verifying Hash Integrity ... sha256+ OK ## Loading fdt from FIT Image at 0e8e9740 ... Using 'conf' configuration Trying 'fdt' fdt subimage Description: unavailable Type: Flat Device Tree Compression: uncompressed Data Start: 0x0e8e9f40 Data Size: 41878 Bytes = 40.9 KiB Architecture: ARM Load Address: 0x00c00000 Hash algo: sha256 Hash value: 507d711cc7ef081404434f0b3beb303553eb60dabda6df617ab2486aa350ace6 Verifying Hash Integrity ... sha256+ OK Loading fdt from 0x0e8e9740 to 0x00c00000 Booting using the fdt blob at 0x00c00000 Loading Kernel Image from 0x0e8f4340 to 0x00008000 ... OK kernel loaded at 0x00008000, end = 0x0030d2a0 Using Device Tree in place at 00c00000, end 00c0d395 ## reserved-memory: mmc@3f000: addr=3f000 size=1000 Adding bank: 0x00000000 - 0x10000000 (size: 0x10000000) Total: 819.212/1261.293 ms Starting kernel ... [ 0.000000] Booting Linux on physical CPU 0x0 [ 0.000000] Linux version 5.10.160 (hxj@luckfox-System-Product-Name) (arm-rockchip830-linux-uclibcgnueabihf-gcc (crosstool-NG 1.24.0) 8.3.0, GN5 [ 0.000000] CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=50c53c7d [ 0.000000] CPU: div instructions available: patching division code [ 0.000000] CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache [ 0.000000] OF: fdt: Machine model: Luckfox Pico Ultra W [ 0.000000] Memory policy: Data cache writeback [ 0.000000] OF: fdt: Reserved memory: failed to reserve memory for node 'drm-logo@00000000': base 0x00000000, size 0 MiB [ 0.000000] Reserved memory: created CMA memory pool at 0x0f600000, size 10 MiB [ 0.000000] OF: reserved mem: initialized node linux,cma, compatible id shared-dma-pool [ 0.000000] cma: Reserved 67584 KiB at 0x0b400000 [ 0.000000] Zone ranges: [ 0.000000] Normal [mem 0x0000000000000000-0x000000000fffffff] [ 0.000000] Movable zone start for each node [ 0.000000] Early memory node ranges [ 0.000000] node 0: [mem 0x0000000000000000-0x000000000fffffff] [ 0.000000] Initmem setup node 0 [mem 0x0000000000000000-0x000000000fffffff] [ 0.000000] CPU: All CPU(s) started in SVC mode. [ 0.000000] Built 1 zonelists, mobility grouping on. Total pages: 65024 [ 0.000000] Kernel command line: user_debug=31 storagemedia=emmc androidboot.storagemedia=emmc androidboot.mode=normal rootwait earlycon=uart85 [ 0.000000] Dentry cache hash table entries: 32768 (order: 5, 131072 bytes, linear) [ 0.000000] Inode-cache hash table entries: 16384 (order: 4, 65536 bytes, linear) [ 0.000000] mem auto-init: stack:off, heap alloc:off, heap free:off [ 0.000000] Memory: 174980K/262144K available (3990K kernel code, 385K rwdata, 1868K rodata, 204K init, 148K bss, 9340K reserved, 77824K cma-re) [ 0.000000] SLUB: HWalign=64, Order=0-3, MinObjects=0, CPUs=1, Nodes=1 [ 0.000000] NR_IRQS: 16, nr_irqs: 16, preallocated irqs: 16 [ 0.000000] arch_timer: cp15 timer(s) running at 24.00MHz (phys). [ 0.000000] clocksource: arch_sys_counter: mask: 0xffffffffffffff max_cycles: 0x588fe9dc0, max_idle_ns: 440795202592 ns [ 0.000007] sched_clock: 56 bits at 24MHz, resolution 41ns, wraps every 4398046511097ns [ 0.000019] Switching to timer-based delay loop, resolution 41ns [ 0.000533] Console: colour dummy device 80x30 [ 0.000573] Calibrating delay loop (skipped), value calculated using timer frequency.. 48.00 BogoMIPS (lpj=240000) [ 0.000591] pid_max: default: 4096 minimum: 301 [ 0.000748] Mount-cache hash table entries: 1024 (order: 0, 4096 bytes, linear) [ 0.000763] Mountpoint-cache hash table entries: 1024 (order: 0, 4096 bytes, linear) [ 0.001318] CPU: Testing write buffer coherency: ok [ 0.001870] Setting up static identity map for 0x81c0 - 0x81f8 [ 0.002343] devtmpfs: initialized [ 0.009719] VFP support v0.3: implementor 41 architecture 2 part 30 variant 7 rev 5 [ 0.009924] clocksource: jiffies: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 19112604462750000 ns [ 0.009945] futex hash table entries: 16 (order: -5, 192 bytes, linear) [ 0.010023] pinctrl core: initialized pinctrl subsystem [ 0.011146] NET: Registered protocol family 16 [ 0.011575] DMA: failed to allocate 0 KiB pool for atomic coherent allocation [ 0.012090] Registered FIQ tty driver [ 0.012392] thermal_sys: Registered thermal governor 'step_wise' [ 0.012399] thermal_sys: Registered thermal governor 'user_space' [ 0.012607] cpuidle: using governor menu [ 0.027540] rockchip-gpio ff380000.gpio: probed /pinctrl/gpio@ff380000 [ 0.028149] rockchip-gpio ff530000.gpio: probed /pinctrl/gpio@ff530000 [ 0.028752] rockchip-gpio ff540000.gpio: probed /pinctrl/gpio@ff540000 [ 0.029453] rockchip-gpio ff550000.gpio: probed /pinctrl/gpio@ff550000 [ 0.030097] rockchip-gpio ff560000.gpio: probed /pinctrl/gpio@ff560000 [ 0.030184] rockchip-pinctrl pinctrl: probed pinctrl [ 0.040652] fiq_debugger fiq_debugger.0: IRQ uart_irq not found [ 0.040675] fiq_debugger fiq_debugger.0: IRQ wakeup not found [ 0.040942] printk: console [ttyFIQ0] enabled [ 0.041110] Registered fiq debugger ttyFIQ0 [ 0.042242] reg-fixed-voltage vdd-arm: Fixed regulator specified with variable voltages [ 0.042275] reg-fixed-voltage: probe of vdd-arm failed with error -22 [ 0.042901] SCSI subsystem initialized [ 0.043112] usbcore: registered new interface driver usbfs [ 0.043156] usbcore: registered new interface driver hub [ 0.043198] usbcore: registered new device driver usb [ 0.043420] mc: Linux media interface: v0.10 [ 0.043463] videodev: Linux video capture interface: v2.00 [ 0.044544] Advanced Linux Sound Architecture Driver Initialized. [ 0.045022] Bluetooth: Core ver 2.22 [ 0.045087] NET: Registered protocol family 31 [ 0.045098] Bluetooth: HCI device and connection manager initialized [ 0.045114] Bluetooth: HCI socket layer initialized [ 0.045126] Bluetooth: L2CAP socket layer initialized [ 0.045146] Bluetooth: SCO socket layer initialized [ 0.045570] rockchip-cpuinfo cpuinfo: SoC : 11061000 [ 0.045593] rockchip-cpuinfo cpuinfo: Serial : 4e9080747fb4b024 [ 0.045977] rockchip,rknpor-powergood ff000000.syscon:rknpor-powergood: probe success! [ 0.046827] clocksource: Switched to clocksource arch_sys_counter [ 0.052880] NET: Registered protocol family 2 [ 0.053099] IP idents hash table entries: 4096 (order: 3, 32768 bytes, linear) [ 0.053566] tcp_listen_portaddr_hash hash table entries: 512 (order: 0, 4096 bytes, linear) [ 0.053598] TCP established hash table entries: 2048 (order: 1, 8192 bytes, linear) [ 0.053622] TCP bind hash table entries: 2048 (order: 1, 8192 bytes, linear) [ 0.053646] TCP: Hash tables configured (established 2048 bind 2048) [ 0.053730] UDP hash table entries: 256 (order: 0, 4096 bytes, linear) [ 0.053751] UDP-Lite hash table entries: 256 (order: 0, 4096 bytes, linear) [ 0.053874] NET: Registered protocol family 1 [ 0.054359] RPC: Registered named UNIX socket transport module. [ 0.054380] RPC: Registered udp transport module. [ 0.054387] RPC: Registered tcp transport module. [ 0.054394] RPC: Registered tcp NFSv4.1 backchannel transport module. [ 0.055307] rockchip-thermal ff3c8000.tsadc: tsadc is probed successfully! [ 0.056305] Initialise system trusted keyrings [ 0.056545] workingset: timestamp_bits=30 max_order=16 bucket_order=0 [ 0.060068] squashfs: version 4.0 (2009/01/31) Phillip Lougher [ 0.060808] NFS: Registering the id_resolver key type [ 0.060867] Key type id_resolver registered [ 0.060876] Key type id_legacy registered [ 0.060918] jffs2: version 2.2. (NAND) © 2001-2006 Red Hat, Inc. [ 0.148684] Key type asymmetric registered [ 0.148706] Asymmetric key parser 'x509' registered [ 0.148728] io scheduler mq-deadline registered [ 0.149121] rockchip-usb2phy ff3e0000.usb2-phy: IRQ index 0 not found [ 0.151798] pwm-backlight backlight: supply power not found, using dummy regulator [ 0.154444] dma-pl330 ff420000.dma-controller: Loaded driver for PL330 DMAC-241330 [ 0.154465] dma-pl330 ff420000.dma-controller: DBUFF-128x8bytes Num_Chans-8 Num_Peri-32 Num_Events-16 [ 0.155233] rockchip-pvtm ff240000.pvtm: pvtm@0 probed [ 0.155396] rockchip-pvtm ff390000.pvtm: pvtm@0 probed [ 0.155717] rockchip-system-monitor rockchip-system-monitor: system monitor probe [ 0.156248] Serial: 8250/16550 driver, 6 ports, IRQ sharing disabled [ 0.156914] ff4b0000.serial: ttyS1 at MMIO 0xff4b0000 (irq = 38, base_baud = 1500000) is a 16550A [ 0.160977] rockchip-drm display-subsystem: bound ff990000.vop (ops 0xb0424e8c) [ 0.161037] rockchip-rgb ff000000.syscon:rgb: [drm:rockchip_rgb_bind] *ERROR* failed to find panel or bridge: -517 Seeding 256 bits and crediting [ 0.161198] random: crng init done Saving 256 bits of creditable seed for next boot [ 0.164770] panel-simple panel: supply power not found, using dummy regulator Starting syslogd: OK [ 0.173679] brd: module loaded [ 0.178758] loop: module loaded Starting klogd: [ 0.180840] rk_gmac-dwmac ffa80000.ethernet: IRQ eth_lpi not found OK [ 0.181052] rk_gmac-dwmac ffa80000.ethernet: PTP uses main clock [ 0.181098] rk_gmac-dwmac ffa80000.ethernet: no regulator found [ 0.181112] rk_gmac-dwmac ffa80000.ethernet: clock input or output? (input). Running sysctl: [ 0.181123] rk_gmac-dwmac ffa80000.ethernet: Can not read property: tx_delay. [ 0.181133] rk_gmac-dwmac ffa80000.ethernet: set tx_delay to 0xffffffff [ 0.181143] rk_gmac-dwmac ffa80000.ethernet: Can not read property: rx_delay. [ 0.181152] rk_gmac-dwmac ffa80000.ethernet: set rx_delay to 0xffffffff [ 0.181223] rk_gmac-dwmac ffa80000.ethernet: integrated PHY? (yes). OK [ 0.181239] rk_gmac-dwmac ffa80000.ethernet: cannot get clock mac_clk_rx [ 0.181252] rk_gmac-dwmac ffa80000.ethernet: cannot get clock mac_clk_tx Populating /dev using udev: [ 0.181281] rk_gmac-dwmac ffa80000.ethernet: cannot get clock clk_mac_speed [ 0.181291] rk_gmac-dwmac ffa80000.ethernet: clock input from PHY [ 0.181539] rk_gmac-dwmac ffa80000.ethernet: init for RMII [ 0.181729] rk_gmac-dwmac ffa80000.ethernet: User ID: 0x30, Synopsys ID: 0x51 [ 0.181749] rk_gmac-dwmac ffa80000.ethernet: DWMAC4/5 [ 0.181762] rk_gmac-dwmac ffa80000.ethernet: DMA HW capability register supported [ 0.181771] rk_gmac-dwmac ffa80000.ethernet: RX Checksum Offload Engine supported [ 0.181780] rk_gmac-dwmac ffa80000.ethernet: TX Checksum insertion supported [ 0.181789] rk_gmac-dwmac ffa80000.ethernet: Wake-Up On Lan supported [ 0.181796] rk_gmac-dwmac ffa80000.ethernet: TSO supported [ 0.181805] rk_gmac-dwmac ffa80000.ethernet: Enable RX Mitigation via HW Watchdog Timer [ 0.181815] rk_gmac-dwmac ffa80000.ethernet: TSO feature enabled [ 0.181825] rk_gmac-dwmac ffa80000.ethernet: Using 40 bits DMA width [ 0.187999] ehci_hcd: USB 2.0 'Enhanced' Host Controller (EHCI) Driver [ 0.188377] phy phy-ff3e0000.usb2-phy.0: illegal mode [ 0.188398] xhci-hcd xhci-hcd.0.auto: xHCI Host Controller [ 0.188435] xhci-hcd xhci-hcd.0.auto: new USB bus registered, assigned bus number 1 [ 0.188599] xhci-hcd xhci-hcd.0.auto: hcc params 0x0220fe64 hci version 0x110 quirks 0x0000000022010010 [ 0.188647] xhci-hcd xhci-hcd.0.auto: irq 66, io mem 0xffb00000 [ 0.189662] hub 1-0:1.0: USB hub found [ 0.189729] hub 1-0:1.0: 1 port detected [ 0.190058] xhci-hcd xhci-hcd.0.auto: xHCI Host Controller [ 0.190089] xhci-hcd xhci-hcd.0.auto: new USB bus registered, assigned bus number 2 [ 0.190115] xhci-hcd xhci-hcd.0.auto: Host supports USB 3.0 SuperSpeed [ 0.190191] usb usb2: We don't know the algorithms for LPM for this host, disabling LPM. [ 0.190853] hub 2-0:1.0: USB hub found [ 0.190914] hub 2-0:1.0: config failed, hub doesn't have any ports! (err -19) [ 0.191247] usbcore: registered new interface driver usb-storage [ 0.191396] gadgetfs: USB Gadget filesystem, version 24 Aug 2004 [ 0.191413] udc-core: couldn't find an available UDC - added [g_mass_storage] to list of pending drivers [ 0.192759] rockchip-rtc ff1c0000.rtc: registered as rtc0 [ 0.192833] rockchip-rtc ff1c0000.rtc: setting system clock to 2021-01-01T12:08:37 UTC (1609502917) [ 0.193070] i2c /dev entries driver [ 0.194334] Goodix-TS 3-0014: supply AVDD28 not found, using dummy regulator [ 0.194492] Goodix-TS 3-0014: supply VDDIO not found, using dummy regulator [ 0.194791] Goodix-TS 3-0014: i2c test failed attempt 1: -6 [ 0.226989] Goodix-TS 3-0014: i2c test failed attempt 2: -6 [ 0.266829] Goodix-TS 3-0014: I2C communication failure: -6 [ 0.269367] usbcore: registered new interface driver uvcvideo [ 0.269393] USB Video Class driver (1.1.1) [ 0.270004] Bluetooth: HCI UART driver ver 2.3 [ 0.270022] Bluetooth: HCI UART protocol H4 registered [ 0.270196] cpu cpu0: leakage=15 [ 0.270976] Synopsys Designware Multimedia Card Interface Driver [ 0.271925] dtbocfg: 0.1.0 [ 0.271968] dtbocfg: OK [ 0.273160] dwmmc_rockchip ffa90000.mmc: IDMAC supports 32-bit address mode. [ 0.273203] dwmmc_rockchip ffa90000.mmc: Using internal DMA controller. [ 0.273222] dwmmc_rockchip ffa90000.mmc: Version ID is 270a [ 0.273259] dwmmc_rockchip ffa90000.mmc: DW MMC controller at irq 55,32 bit host data width,256 deep fifo [ 0.273366] mmc_host mmc0: card is non-removable. [ 0.273601] mmc_host mmc0: Bus speed (slot 0) = 400000Hz (slot req 400000Hz, actual 400000HZ div = 0) [ 0.274166] dwmmc_rockchip ffaa0000.mmc: No normal pinctrl state [ 0.274190] dwmmc_rockchip ffaa0000.mmc: No idle pinctrl state [ 0.274337] dwmmc_rockchip ffaa0000.mmc: IDMAC supports 32-bit address mode. [ 0.274370] dwmmc_rockchip ffaa0000.mmc: Using internal DMA controller. [ 0.274385] dwmmc_rockchip ffaa0000.mmc: Version ID is 270a [ 0.274423] dwmmc_rockchip ffaa0000.mmc: DW MMC controller at irq 56,32 bit host data width,256 deep fifo [ 0.274523] dwmmc_rockchip ffaa0000.mmc: allocated mmc-pwrseq [ 0.274539] mmc_host mmc1: card is non-removable. [ 0.275987] rv1106-acodec ff480000.acodec: current soc_id: rv1106 [ 0.276077] rv1106-acodec ff480000.acodec: Use pa_ctl_gpio and pa_ctl_delay_ms: 0 [ 0.277738] NET: Registered protocol family 17 [ 0.277922] Bluetooth: RFCOMM TTY layer initialized [ 0.277946] Bluetooth: RFCOMM socket layer initialized [ 0.277979] Bluetooth: RFCOMM ver 1.11 [ 0.278033] [BT_RFKILL]: Enter rfkill_rk_init [ 0.278043] [WLAN_RFKILL]: Enter rfkill_wlan_init [ 0.278629] [BT_RFKILL]: bluetooth_platdata_parse_dt: get property: uart_rts_gpios = 5. [ 0.278672] [BT_RFKILL]: bluetooth_platdata_parse_dt: get property: BT,wake_gpio = 2. [ 0.278694] [BT_RFKILL]: bluetooth_platdata_parse_dt: get property: BT,wake_host_irq = 34. [ 0.278707] [BT_RFKILL]: bluetooth_platdata_parse_dt: clk_get failed!!!. [ 0.278761] [BT_RFKILL]: Failed to get bt_default_wake_host gpio. [ 0.278807] rfkill_bt: probe of wireless-bluetooth failed with error -1 [ 0.278881] Key type dns_resolver registered [ 0.279809] Loading compiled-in X.509 certificates [ 0.295042] mmc_host mmc1: Bus speed (slot 0) = 400000Hz (slot req 400000Hz, actual 400000HZ div = 0) [ 0.308528] rockchip-drm display-subsystem: bound ff990000.vop (ops 0xb0424e8c) [ 0.308606] rockchip-drm display-subsystem: bound ff000000.syscon:rgb (ops 0xb04259ec) [ 0.308871] rockchip-drm display-subsystem: failed to parse resources for logo display [ 0.310520] rockchip-vop ff990000.vop: [drm:vop_crtc_atomic_enable] Update mode to 720x720p49, type: 17 [ 0.320767] mmc1: queuing unknown CIS tuple 0x10 (5 bytes) [ 0.326008] mmc_host mmc1: Bus speed (slot 0) = 49500000Hz (slot req 50000000Hz, actual 49500000HZ div = 0) [ 0.326192] mmc1: queuing unknown CIS tuple 0x10 (5 bytes) [ 0.327274] mmc1: new SDIO card at address e9ea [ 0.331371] mmc_host mmc0: Bus speed (slot 0) = 49500000Hz (slot req 52000000Hz, actual 49500000HZ div = 0) [ 0.335078] mmc0: new high speed MMC card at address 0001 [ 0.335516] mmcblk0: mmc0:0001 TWSC 7.13 GiB [ 0.335601] mmcblk0boot0: mmc0:0001 TWSC partition 1 4.00 MiB [ 0.335677] mmcblk0boot1: mmc0:0001 TWSC partition 2 4.00 MiB [ 0.335856] mmcblk0rpmb: mmc0:0001 TWSC partition 3 4.00 MiB, chardev (247:0) [ 0.336270] mmcblk0: p1(env) p2(idblock) p3(uboot) p4(boot) p5(oem) p6(userdata) p7(rootfs) [ 0.592871] Console: switching to colour frame buffer device 90x45 [ 0.609117] rockchip-drm display-subsystem: [drm] fb0: rockchipdrmfb frame buffer device [ 0.609814] [drm] Initialized rockchip 3.0.0 20140818 for display-subsystem on minor 0 [ 0.610306] input: adc-keys as /devices/platform/adc-keys/input/input0 [ 0.689547] ALSA device list: [ 0.689574] #0: rv1106-acodec [ 0.699613] EXT4-fs (mmcblk0p7): INFO: recovery required on readonly filesystem [ 0.699639] EXT4-fs (mmcblk0p7): write access will be enabled during recovery [ 0.739249] EXT4-fs (mmcblk0p7): recovery complete [ 0.740906] EXT4-fs (mmcblk0p7): mounted filesystem with ordered data mode. Opts: (null) [ 0.740976] VFS: Mounted root (ext4 filesystem) readonly on device 179:7. [ 0.741113] devtmpfs: mounted [ 0.741313] Freeing unused kernel memory: 204K [ 0.741324] Kernel memory protection not selected by kernel config. [ 0.741360] Run /sbin/init as init process [ 0.746627] process '/bin/busybox' started with executable stack [ 0.800628] EXT4-fs (mmcblk0p7): re-mounted. Opts: (null) [ 1.017980] udevd[98]: starting version 3.2.7 [ 1.027669] udevd[98]: specified group 'input' unknown [ 1.028737] udevd[98]: specified group 'kvm' unknown [ 1.056428] udevd[99]: starting eudev-3.2.7 done resize2fs 1.46.5 (30-Dec-2021) The filesystem is already 1572864 (4k) blocks long. Nothing to do! e2fsck 1.46.5 (30-Dec-2021) userdata: recovering journal userdata: clean, 15/65536 files, 18585/262144 blocks [ 2.337444] EXT4-fs (mmcblk0p6): mounted filesystem with ordered data mode. Opts: (null) [ 2.337494] ext4 filesystem being mounted at /userdata supports timestamps until 2038 (0x7fffffff) resize2fs 1.46.5 (30-Dec-2021) The filesystem is already 262144 (1k) blocks long. Nothing to do! tune2fs 1.46.5 (30-Dec-2021) e2fsck 1.46.5 (30-Dec-2021) oem: recovering journal oem: clean, 372/32768 files, 12024/131072 blocks [ 2.528590] EXT4-fs (mmcblk0p5): mounted filesystem with ordered data mode. Opts: (null) resize2fs 1.46.5 (30-Dec-2021) The filesystem is already 131072 (4k) blocks long. Nothing to do! tune2fs 1.46.5 (30-Dec-2021) Initializing random number generator... done. Starting fcgiwrap daemon: OK Starting nginx... nginx: [warn] duplicate MIME type "text/html" in /oem/usr/etc/nginx/nginx.conf:43 /dev/block/by-name/userdata on /userdata type ext4 (rw,relatime) Starting system message bus: [ 3.807762] rk_dvbm ffa70000.rkdvbm: probe start [ 3.807800] rk_dvbm ffa70000.rkdvbm: dvbm ctx ae52bfa0 [ 3.808102] rk_dvbm ffa70000.rkdvbm: probe success [ 3.822205] sc3336 4-0030: driver version: 00.01.01 [ 3.822310] sc3336 4-0030: Failed to get pwdn-gpios [ 3.822324] sc3336 4-0030: could not get default pinstate [ 3.822333] sc3336 4-0030: could not get sleep pinstate dbus[180]: Unknown username "pulse" in message bus configuration file [ 3.822354] sc3336 4-0030: supply avdd not found, using dummy regulator done [ 3.822581] sc3336 4-0030: supply dovdd not found, using dummy regulator [ 3.822646] sc3336 4-0030: supply dvdd not found, using dummy regulator [ 3.833239] sc3336 4-0030: Detected OV00cc41 sensor [ 3.844537] rockchip-pinctrl pinctrl: pin gpio3-20 already requested by 4-0030; cannot claim for 4-0031 Starting bluetoothd: [ 3.844562] rockchip-pinctrl pinctrl: pin-116 (4-0031) status -22 [ 3.844577] rockchip-pinctrl pinctrl: could not request pin 116 (gpio3-20) from group mipi-refclk-out0 on device rockchip-pinctrl [ 3.844588] mis5001 4-0031: Error applying setting, reverse things back OK [ 3.844610] mis5001: probe of 4-0031 failed with error -22 [ 3.874595] rkcifhw ffa10000.rkcif: no iommu attached, using non-iommu buffers [ 3.874620] rkcifhw ffa10000.rkcif: No reserved memory region assign to CIF [ 3.875036] rkcif rkcif-mipi-lvds: rkcif driver version: v00.02.00 [ 3.875150] rkcif rkcif-mipi-lvds: attach to cif hw node [ 3.875162] rkcif rkcif-mipi-lvds: failed to get dphy hw node Starting network: [ 3.875173] rkcif rkcif-mipi-lvds: rkcif wait line 0 [ 3.875183] rkcif rkcif-mipi-lvds: rkcif fastboot reserve bufs num 3 [ 3.875197] : terminal subdev does not exist [ 3.875207] : terminal subdev does not exist [ 3.875215] : terminal subdev does not exist [ 3.875223] : terminal subdev does not exist [ 3.875232] : get_remote_sensor: video pad[0] is null [ 3.875240] : rkcif_update_sensor_info: stream[0] get remote sensor_sd failed! [ 3.875251] : rkcif_scale_set_fmt: req(80, 60) src out(0, 0) [ 3.875259] : get_remote_sensor: video pad[0] is null [ 3.875265] : rkcif_update_sensor_info: stream[0] get remote sensor_sd failed! [ 3.875273] : rkcif_scale_set_fmt: req(80, 60) src out(0, 0) [ 3.875281] : get_remote_sensor: video pad[0] is null [ 3.875288] : rkcif_update_sensor_info: stream[0] get remote sensor_sd failed! [ 3.875298] : rkcif_scale_set_fmt: req(80, 60) src out(0, 0) [ 3.875306] : get_remote_sensor: video pad[0] is null [ 3.875312] : rkcif_update_sensor_info: stream[0] get remote sensor_sd failed! [ 3.875321] : rkcif_scale_set_fmt: req(80, 60) src out(0, 0) [ 3.888070] rkcif rkcif-mipi-lvds: No memory-region-thunderboot specified [ 3.889294] rockchip-mipi-csi2-hw ffa20000.mipi-csi2-hw: enter mipi csi2 hw probe! [ 3.889454] rockchip-mipi-csi2-hw ffa20000.mipi-csi2-hw: probe success, v4l2_dev:mipi-csi2-hw! [ 3.889583] rockchip-mipi-csi2-hw ffa30000.mipi-csi2-hw: enter mipi csi2 hw probe! [ 3.889687] rockchip-mipi-csi2-hw ffa30000.mipi-csi2-hw: probe success, v4l2_dev:mipi-csi2-hw! [ 3.890123] rockchip-mipi-csi2 mipi0-csi2: attach to csi2 hw node [ 3.890187] rkcif rkcif-mipi-lvds: Entity type for entity rockchip-mipi-csi2 was not initialized! [ 3.890203] rockchip-mipi-csi2: Async registered subdev [ 3.890216] rockchip-mipi-csi2: probe success, v4l2_dev:rkcif-mipi-lvds! [ 3.912805] rkisp_hw ffa00000.rkisp: is_thunderboot: 0 [ 3.912833] rkisp_hw ffa00000.rkisp: Missing rockchip,grf property [ 3.912875] rkisp_hw ffa00000.rkisp: max input:0x0@0fps OK [ 3.913047] rkisp_hw ffa00000.rkisp: get sram size:253952 [ 3.913062] rkisp_hw ffa00000.rkisp: no iommu attached, using non-iommu buffers [ 3.913072] rkisp_hw ffa00000.rkisp: No reserved memory region. default cma area! [ 3.913480] rkisp rkisp-vir0: rkisp driver version: v02.05.00 Starting ntpd: [ 3.913649] rkisp rkisp-vir0: No memory-region-thunderboot specified [ 3.920987] rkisp rkisp-vir0: Entity type for entity rkisp-isp-subdev was not initialized! [ 3.951080] rockchip-csi2-dphy-hw ff3e8000.csi2-dphy-hw: csi2 dphy hw probe successfully! [ 3.965504] rockchip-csi2-dphy csi2-dphy0: dphy0 matches m00_b_sc3336 4-0030:bus type 5 [ 3.965531] rockchip-csi2-dphy csi2-dphy0: csi2 dphy0 probe successfully! 0 [ 4.251498] rkcif rkcif-mipi-lvds: clear unready subdev num: 1 [ 4.252853] rkcif-mipi-lvds: Async subdev notifier completed [ 4.253907] rkisp-vir0: Async subdev notifier completed [ 4.255015] rkisp rkisp-vir0: clear unready subdev num: 0 [ 4.271376] rga: rga2, irq = 40, match scheduler [ 4.272043] rga: rga2 hardware loaded successfully, hw_version:3.3.87975. [ 4.272068] rga: rga2 probe successfully [ 4.272341] rga_iommu: IOMMU binding successfully, default mapping core[0x4] [ 4.273301] rga: Module initialized. v1.3.1 [ 4.294691] mpp_vcodec: loading out-of-tree module taints kernel. [ 4.310409] mpp_vcodec: init new [ 4.310561] mpp_service mpp-srv: 424abb9b author: Yandong Lin 2024-04-29 [mpp_enc]: fix wrap enc sw timeout when resolution switch [ 4.310577] mpp_service mpp-srv: probe start [ 4.311717] mpp_rkvenc_540c ffa50000.rkvenc: probing start OK [ 4.311964] mpp_rkvenc_540c ffa50000.rkvenc: probing finish [ 4.312397] mpp_vepu_pp ffa60000.rkvenc-pp: probe device [ 4.312493] mpp_vepu_pp ffa60000.rkvenc-pp: shared_rst_a_pp is not found! [ 4.312505] vepu_pp_init:526: No aclk reset resource define [ 4.312515] mpp_vepu_pp ffa60000.rkvenc-pp: shared_rst_h_pp is not found! Input rkcif-mipi-lvds Format:SBGGR10_1X10 Size:2304x1296@30fps Offset(0,0) [ 4.312522] vepu_pp_init:529: No hclk reset resource define [ 4.313753] mpp_vepu_pp ffa60000.rkvenc-pp: probing finish [ 4.314006] mpp_service mpp-srv: probe success [ 4.340565] RKNPU ff660000.npu: RKNPU: rknpu iommu device-tree entry not found!, using non-iommu mode [ 4.341763] RKNPU ff660000.npu: RKNPU: Initialized RKNPU driver: v0.9.2 for 20230825 [ 4.341876] RKNPU ff660000.npu: dev_pm_opp_set_regulators: no regulator (rknpu) found: -19 [ 4.392470] rockit_load start [ 4.408445] rockit_load end [ 4.417620] rve: rve_irq, irq = 57, match scheduler / [ 4.417831] rve: Driver loaded successfully rve[2] ver:[2021]58.1a [ 4.417850] rve: probe successfully Starting sshd: [ 4.419577] rve: Module initialized. v1.0.6 sc3336 9940 1 cmd parse result: input file name : /oem/usr/share/speaker_test.wav [ 4.746352] rk_gmac-dwmac ffa80000.ethernet eth0: PHY [stmmac-0:02] driver [RK630 PHY] (irq=POLL) output file name : (null) [ 4.746684] dwmac4: Master AXI performs any burst length loop count : 1 [ 4.746712] rk_gmac-dwmac ffa80000.ethernet eth0: No Safety Features support found channel number : 1 [ 4.746733] rk_gmac-dwmac ffa80000.ethernet eth0: PTP not supported by HW open sound rate : 8000 [ 4.747071] rk_gmac-dwmac ffa80000.ethernet eth0: configuring for phy/rmii link mode open sound channel : 2 [ 4.751016] cfg80211: Loading compiled-in X.509 certificates for regulatory database input stream rate : 8000 [ 4.757565] vsys dev open 27 input channel : 2 [ 4.764043] udevd[337]: failed to execute '/lib/udev/v4l_id' 'v4l_id /dev/video0': No such file or directory bit_width : 16 [ 4.765354] udevd[338]: failed to execute '/lib/udev/v4l_id' 'v4l_id /dev/video1': No such file or directory frame_number : 4 [ 4.768595] udevd[339]: failed to execute '/lib/udev/v4l_id' 'v4l_id /dev/video2': No such file or directory frame_length : 1024 [ 4.774178] udevd[342]: failed to execute '/lib/udev/v4l_id' 'v4l_id /dev/video3': No such file or directory sound card name : hw:0,0 [ 4.775307] udevd[343]: failed to execute '/lib/udev/v4l_id' 'v4l_id /dev/video4': No such file or directory device id : 0 [ 4.776456] udevd[344]: failed to execute '/lib/udev/v4l_id' 'v4l_id /dev/video5': No such file or directory set volume curve : 0 [ 4.778083] udevd[345]: failed to execute '/lib/udev/v4l_id' 'v4l_id /dev/video6': No such file or directory set volume : 50 [ 4.820573] cfg80211: Loaded X.509 cert 'sforshee: 00b28ddf47aef9cea7' set mute : 0 [ 4.820748] platform regulatory.0: Direct firmware load for regulatory.db failed with error -2 set track_mode : 0 [ 4.820767] cfg80211: failed to load regulatory.db get volume : 0 get mute : 0 get track_mode : 0 query stat : 0 pause and resume chn : 0 save file : 0 query save file stat : 0 clear buf : 0 get attribute : 0 clear attribute : 0 set loopback mode : 0 vqe enable : 0 adec input file name : (null) rockit log path (null), log_size = 0, can use export rt_log_path=, export rt_log_size= change log_file = (nil) RTVersion 12:08:42-048 {dump :064} --------------------------------------------------------- RTVersion 12:08:42-048 {dump :065} rockit version: git-4720dc10a Tue Apr 30 15:47:55 2024 +0800 RTVersion 12:08:42-048 {dump :066} rockit building: built- 2024-04-30 15:53:43 RTVersion 12:08:42-048 {dump :067} --------------------------------------------------------- [ 5.005141] libaes: exports duplicate symbol aes_decrypt (owned by kernel) rockit default level 4, can use export rt_log_level=x, x=0,1,2,3,4,5,6 change [ 5.005470] libaes: exports duplicate symbol aes_decrypt (owned by kernel) (null) 12:08:42-048 {read_log_level :098} text is all=4 (null) 12:08:42-048 {read_log_level :100} module is all, log_level is 4 cmpi 12:08:42-066 {main :823} start running loop count = 0 (null) 12:08:42-070 {monitor_log_level :149} #Start monitor_log_level thread, arg:(nil) OK cmpi 12:08:42-161 {test_init_mpi_ao :226} Set volume curve type: 0 cmpi 12:08:42-164 {commandThread :376} test info : mute = 0, volume = 50 cmpi 12:08:42-167 {sendDataThread :309} params->s32ChnIndex : 0 [ 5.083627] aicbsp_init /etc/init.d/S50usbdevice: line 144: can't open : no such file [ 5.083648] RELEASE_DATE:2025_0410_b99ca8b6 Debug: configfs_init [ 5.083657] aicbsp_resv_mem_init insmod: can't insert 'libaes.ko': invalid module format [ 5.120992] file system registered mkdir: can't create directory '/sys/kernel/config/usb_gadget/rockchip/functions/mtp.gs0': No such file or directory [ 5.136941] using random self ethernet address [ 5.136966] using random host ethernet address mkdir: can't create directory '/sys/kernel/config/usb_gadget/rockchip/functions/acm.gs6': No such file or directory [ 5.149777] Mass Storage Function, version: 2009/09/11 [ 5.149806] LUN: removable file: (no medium) [ 5.227257] read descriptors [ 5.227329] read strings [ 5.315218] aicbsp: aicbsp_set_subsys, subsys: AIC_WIFI, state to: 1 [ 5.315248] aicbsp: aicbsp_set_subsys, power state change to 1 dure to AIC_WIFI [ 5.315255] aicbsp: aicbsp_platform_power_on [ 5.339142] aicbsp: aicbsp_sdio_probe:1 vid:0xC8A1 did:0xC08D [ 5.339284] aicbsp: aicbsp_sdio_probe:2 vid:0xC8A1 did:0xC18D [ 5.339298] aicbsp: aicbsp_sdio_probe after replace:1 [ 5.339309] AICWFDBG(LOGINFO) aicwf_sdio_chipmatch USE AIC8800DC [ 5.339316] the device is PRODUCT_ID_AIC8800DC [ 5.339325] aicbsp: aicbsp_get_feature, set FEATURE_SDIO_CLOCK 50 MHz [ 5.339332] aicbsp: aicwf_sdio_reg_init [ 5.339535] aicbsp: Set SDIO Clock 50 MHz [ 5.342726] AICWFDBG(LOGINFO) btenable = 1 [ 5.342749] AICWFDBG(LOGINFO) aicbsp: aicbsp_driver_fw_init, chip rev: 7 [ 5.342761] rwnx_load_firmware :firmware path = /oem/usr/ko/aic8800dc_fw/fw_patch_table_8800dc_u02.bin [ 5.348736] file md5:34860725322202bfc2d80843297562ee [ 5.348836] AICWFDBG(LOGDEBUG) aicbt_patch_info_unpack head_t->len:6 base_len:4 [ 5.348846] AICWFDBG(LOGDEBUG) aicbt_patch_info_unpack memcpy_len:5 [ 5.348856] AICWFDBG(LOGDEBUG) aicbt_patch_info_unpack adid_addrinf:194b44 addr_adid:1017d8 [ 5.348863] AICWFDBG(LOGDEBUG) aicbt_patch_info_unpack id:0 addr:194000 [ 5.348871] rwnx_plat_bin_fw_upload_android [ 5.348880] rwnx_load_firmware :firmware path = /oem/usr/ko/aic8800dc_fw/fw_adid_8800dc_u02.bin [ 5.349349] file md5:95d10e6288e4d3413c0e3508cb9d711a [ 5.350013] rwnx_plat_bin_fw_upload_android [ 5.350031] rwnx_load_firmware :firmware path = /oem/usr/ko/aic8800dc_fw/fw_patch_8800dc_u02.bin cmpi 12:08:42-769 {sendDataThread :352} eof [ 5.351559] file md5:675951fc926375001f974d729f097164 [ 5.356417] AICWFDBG(LOGDEBUG) [0x40506004]: 0x04318000 [ 5.356628] AICWFDBG(LOGDEBUG) [0x40506004]: 0x04338000 [ 5.357928] AICWFDBG(LOGDEBUG) aicbt_ext_patch_data_load ext_patch_file_name:fw_patch_8800dc_u02_ext0.bin ext_patch_id:0 ext_patch_addr:1 [ 5.357945] rwnx_plat_bin_fw_upload_android [ 5.357954] rwnx_load_firmware :firmware path = /oem/usr/ko/aic8800dc_fw/fw_patch_8800dc_u02_ext0.bin [ 5.362354] file md5:d783d229be5a485fdb39cc018abaf55b [ 5.376676] aicbt_patch_table_load bt btmode[1]:1 [ 5.376695] aicbt_patch_table_load bt uart_baud[1]:1500000 [ 5.376703] aicbt_patch_table_load bt uart_flowctrl[1]:1 [ 5.376710] aicbt_patch_table_load bt lpm_enable[1]:0 [ 5.376718] aicbt_patch_table_load bt tx_pwr[1]:28463 [ 5.382231] aicbsp: bt patch version: - Mar 17 2025 11:27:16 - git a6547a6 [ 5.382295] ############ aicwifi_init begin [ 5.382619] AICWFDBG(LOGINFO) chip_id=7, chip_sub_id=1!! [ 5.382782] AICWFDBG(LOGDEBUG) set_bbpll_config rd_mem_addr_cfm.memdata:c [ 5.382801] AICWFDBG(LOGINFO) set_bbpll_config Crystal not provided by CPU [ 5.383012] AICWFDBG(LOGDEBUG) [0x40500010]=6 [ 5.386530] ############ system_config_8800dc done [ 5.386543] AICWFDBG(LOGTRACE) >>> rwnx_plat_patch_load() [ 5.386548] AICWFDBG(LOGINFO) testmode=0 [ 5.386554] AICWFDBG(LOGINFO) rwnx_plat_patch_loading [ 5.386560] u02 is loaing ############### [ 5.386566] rwnx_plat_bin_fw_upload_android [ 5.386577] rwnx_load_firmware :firmware path = /oem/usr/ko/aic8800dc_fw/fmacfw_patch_8800dc_u02.bin [ 5.392826] file md5:ec8ee791723f4bf9825a6c153a7f0a8f [ 5.400526] AICWFDBG(LOGINFO) dpd calib & write [ 5.400548] aicwf_dpd_calib_8800dc [ 5.400716] AICWFDBG(LOGERROR) misc_ram_addr=120ebc [ 5.401301] AICWFDBG(LOGTRACE) bit_mask:ad03e777,8ff693a2,7584ddd,86172087 [ 5.401313] rwnx_plat_bin_fw_upload_android [ 5.401323] rwnx_load_firmware :firmware path = /oem/usr/ko/aic8800dc_fw/fmacfw_calib_8800dc_u02.bin [ 5.407240] file md5:061790c6181e5974a4c44c515e6d0b69 [ 5.416628] AICWFDBG(LOGINFO) Start app: 00130009, 4 [ 5.636219] ############ rwnx_plat_patch_load done [ 5.637013] AICWFDBG(LOGINFO) wifisetting_cfg_addr=11019c, ldpc_cfg_addr=120980, agc_cfg_addr=120180, txgain_cfg_addr=120000 [ 5.638969] ### Upload fmacfw_patch_tbl_8800dc_u02.bin [ 5.638989] rwnx_load_firmware :firmware path = /oem/usr/ko/aic8800dc_fw/fmacfw_patch_tbl_8800dc_u02.bin [ 5.643401] file md5:c0538d7493963b1f37938e6e87f9e304 [ 5.643418] tbl size = 1008 [ 5.643426] AICWFDBG(LOGINFO) FMACFW_PATCH_TBL_8800DC_U02_DESCRIBE_BASE = 187c00 [ 5.643687] di Mar 14 2025 12:29:38 - g09cea8d [ 5.643696] patch_tbl: 110888 181219 [ 5.643868] patch_tbl: 1108ec 184d59 [ 5.644027] patch_tbl: 110874 181279 [ 5.644186] patch_tbl: 110658 181b09 [ 5.644346] patch_tbl: 1107dc 1874dd [ 5.644498] patch_tbl: 11055c 184135 [ 5.644654] patch_tbl: 110758 187485 [ 5.644813] patch_tbl: 110620 187631 [ 5.644969] patch_tbl: 1107e0 181b99 [ 5.645134] patch_tbl: 110838 181dd5 [ 5.645339] patch_tbl: 1104f4 182045 [ 5.645497] patch_tbl: 110490 182f6d [ 5.645649] patch_tbl: 110420 1822b1 [ 5.645808] patch_tbl: 11048c 1823cd [ 5.645963] patch_tbl: 110688 182471 [ 5.646119] patch_tbl: 110738 182ead [ 5.646275] patch_tbl: 110528 1877a1 [ 5.646428] patch_tbl: 110554 182fc1 [ 5.646587] patch_tbl: 110798 183615 [ 5.646742] patch_tbl: 1106dc 183061 [ 5.648937] patch_tbl: 110584 1830fd [ 5.649129] patch_tbl: 110588 1832d5 [ 5.649302] patch_tbl: 110634 1854e1 [ 5.649467] patch_tbl: 110638 1856b9 [ 5.649632] patch_tbl: 110640 1858c1 [ 5.649791] patch_tbl: 11086c 18597d [ 5.649948] patch_tbl: 1105fc 1859d9 [ 5.650101] patch_tbl: 1105f0 18655d [ 5.650255] patch_tbl: 110860 185641 [ 5.650411] patch_tbl: 11081c 185131 [ 5.650565] patch_tbl: 1105a4 185dc1 [ 5.650779] patch_tbl: 1105c8 185e91 [ 5.650940] patch_tbl: 110810 1851e9 [ 5.651097] patch_tbl: 1108c4 183869 [ 5.651252] patch_tbl: 1108c8 183705 [ 5.651408] patch_tbl: 110628 1839e1 [ 5.651562] patch_tbl: 110750 18664d [ 5.651718] patch_tbl: 1106d8 186691 [ 5.651876] patch_tbl: 11085c 183e45 [ 5.652032] patch_tbl: 110518 186945 [ 5.652190] patch_tbl: 1105e0 181f7d [ 5.652346] patch_tbl: 1107d8 18368d [ 5.652503] patch_tbl: 1103d0 1869a5 [ 5.652656] patch_tbl: 1106c8 186f81 [ 5.652810] patch_tbl: 11056c 186f4d [ 5.652965] patch_tbl: 1106b4 185309 [ 5.653121] patch_tbl: 110510 187071 [ 5.653279] patch_tbl: 110550 18710d [ 5.653466] patch_tbl: 1104ec 1842a1 [ 5.653626] patch_tbl: 1106d4 187389 [ 5.653787] patch_tbl: 11064c 186241 [ 5.653947] patch_tbl: 110494 184675 [ 5.654109] patch_tbl: 110734 184689 [ 5.654268] patch_tbl: 11047c 1873d1 [ 5.654426] patch_tbl: 110740 18757d [ 5.654582] patch_tbl: 110880 1875e9 [ 5.654738] patch_tbl: 110054 181b09 [ 5.654897] patch_tbl: 11005c 181b09 [ 5.655057] patch_tbl: 110048 182f6d [ 5.655213] patch_tbl: 110088 185929 [ 5.655365] patch_tbl: 1100c4 185309 [ 5.655518] patch_tbl: 110ef0 185b55 [ 5.655670] patch_tbl: 110ec0 183c15 [ 5.655830] patch_tbl: 110da0 183c35 [ 5.655985] patch_tbl: 110dc0 183ded [ 5.656182] patch_tbl: 110e28 183d81 [ 5.656340] patch_tbl: 1100e0 183d2d [ 5.656500] patch_tbl: 110d88 183e29 [ 5.656659] patch_tbl: 110d90 186721 [ 5.656815] patch_tbl: 110e18 183b95 [ 5.660262] patch_tbl: 110bb4 18740d [ 5.660455] patch_tbl: 110960 1835f9 [ 5.660627] patch_tbl: 1109c0 18205d [ 5.660790] patch_tbl: 110f08 182291 [ 5.660946] patch_tbl: 110b1c 183619 [ 5.661106] patch_tbl: 110b24 183619 [ 5.661261] patch_tbl: 110b5c 182585 [ 5.661423] patch_tbl: 110b64 182585 [ 5.661645] patch_tbl: 110b6c 182585 [ 5.661810] patch_tbl: 110b74 182585 [ 5.661970] patch_tbl: 110b7c 182585 [ 5.662129] patch_tbl: 110b8c 182585 [ 5.662289] patch_tbl: 110b44 1858c1 [ 5.662449] patch_tbl: 110ac0 184311 [ 5.662610] patch_tbl: 110aa0 183575 [ 5.662769] patch_tbl: 110aa8 1835dd [ 5.662925] patch_tbl: 110a60 186ea1 [ 5.663082] patch_tbl: 110e20 186f15 [ 5.663238] patch_tbl: 110f3c 187259 [ 5.663395] patch_tbl: 110d28 1872ad cmpi 12:08:43-378 {main :828} end running loop count = 0 [ 5.663556] patch_tbl: 111418 1871a1 [ 5.663712] patch_tbl: 40030084 187c80 [ 5.663865] patch_tbl: 40030000 46e68 [ 5.664023] patch_tbl: 40030004 2778c [ 5.664178] patch_tbl: 40030008 40908 [ 5.664336] patch_tbl: 4003000c 13824 [ 5.664493] patch_tbl: 40030010 13864 [ 5.664649] patch_tbl: 40030014 13868 [ 5.664803] patch_tbl: 40030018 138e4 [ 5.664965] patch_tbl: 4003001c 138e8 [ 5.665122] patch_tbl: 187c80 d0332b00 [ 5.665277] patch_tbl: 187c84 47706008 [ 5.665436] patch_tbl: 187c88 47702001 [ 5.665595] patch_tbl: 187c8c bf00bf00 [ 5.665751] patch_tbl: 187c90 bf004832 [ 5.665906] patch_tbl: 187c94 f3efbf00 [ 5.666062] patch_tbl: 187c98 bf004812 [ 5.666218] patch_tbl: 187c9c 4620bf00 [ 5.666372] patch_tbl: 40030080 fb [ 5.666530] patch_tbl: 4010001c 0 [ 5.666699] ############ aicwf_patch_config_8800dc done [ 5.666710] AICWFDBG(LOGINFO) Read FW mem: 00120000 [ 5.669710] AICWFDBG(LOGINFO) cfm: [00120000] = 00ffd780 [ 5.669727] AICWFDBG(LOGINFO) Start app: 00120000, 5 [ 5.674027] aicbsp: aicbsp_get_feature, set FEATURE_SDIO_CLOCK 50 MHz [ 5.674044] aicsdio: aicwf_sdio_reg_init [ 5.684763] aicbsp: aicbsp_resv_mem_alloc_skb, alloc resv_mem_txdata succuss, id: 0, size: 98304 [ 5.685050] aicbsp: aicbsp_get_feature, set FEATURE_SDIO_CLOCK 50 MHz [ 5.685216] tcp_ack_init [ 5.685234] AICWFDBG(LOGINFO) aicwf_prealloc_txq_alloc size is diff will to be kzalloc [ 5.685259] AICWFDBG(LOGINFO) aicwf_prealloc_txq_alloc txq kzalloc successful sh: write error: No such device [ 5.706836] aicbsp: sdio_err:<aicwf_sdio_bus_pwrctl,1449>: bus down [ 5.917470] ieee80211 phy0: HT supp 1, VHT supp 1, HE supp 1 [ 5.919587] ieee80211 phy0: [ 5.919587] ******************************************************* [ 5.919587] ** CAUTION: USING PERMISSIVE CUSTOM REGULATORY RULES ** [ 5.919587] ******************************************************* [ 5.930360] get_txpwr_max:txpwr_max:20 [ 6.073188] vsys_release, 27 [ 6.073204] vrgn_release, 123 [ 6.073234] vi_release 99 ifconfig: SIOCSIFADDR: No such device ifconfig: SIOCGIFFLAGS: No such device RKSockServer 12:08:44-087 {start :162} accept failed [ 6.073286] venc_release 51 [ 6.807700] rk_gmac-dwmac ffa80000.ethernet eth0: Link is Up - 100Mbps/Full - flow control rx/tx [ 6.970661] of_dma_request_slave_channel: dma-names property of node '/serial@ff4b0000' missing or empty Device setup complete [ 6.970697] dw-apb-uart ff4b0000.serial: failed to request DMA, use interrupt mode /usr/bin/luckfox-config: line 234: warning: command substitution: ignored null byte in input (null) 12:08:45-073 {monitor_log_level :190} monitor_log_level quit Complete configuration loading Found ADC keys device: /dev/input/event0 /root/main.py and /root/boot.py not exist ,pass... OK RTC does not require time calibration [root@luckfox ]# ========================================= === This system is the factory default system, intended for testing purposes only. === === For detailed instructions, visit https://wiki.luckfox.com/. === ========================================= |
| luckfox csi 카메라 테스트 (0) | 2026.04.23 |
|---|
케플러가 600/700 시리즈니 요즘 시대에는 다 된다고 봐야할 듯.
-pl, --power-limit=POWER_LIMITSpecifies maximum power limit in watts. Accepts integer and floating point numbers. it takes an optional argument --scope. Only on supported devices from Kepler family. Value needs to be between Min and Max Power Limit as reported by nvidia-smi. Requires root.-sc, --scope=0/GPU, 1/TOTAL_MODULESpecifies the scope of the power limit. Following are the options: 0/GPU: This only changes power limits for the GPU. 1/Module: This changes the power limits for the module containing multiple components. E.g. GPU and CPU. |
[링크 : https://docs.nvidia.com/deploy/nvidia-smi/]
[링크 : https://developer0hye.tistory.com/690]
+
2026.04.24
범위를 어떻게 확인하지?
| C:\>nvidia-smi -pl 100 Provided power limit 100.00 W is not a valid power limit which should be between 125.00 W and 300.00 W for GPU 00000000:01:00.0 Terminating early due to previous errors. C:\>nvidia-smi -pl 125 Failed to set power management limit for GPU 00000000:01:00.0: Insufficient Permissions Terminating early due to previous errors. |
아무튼 관리자 권한으로 실행된 cmd 창에서만 변경된다.
| C:\>nvidia-smi -pl 125 Power limit for GPU 00000000:01:00.0 was set to 125.00 W from 250.00 W. All done. C:\>nvidia-smi -pl 250 Power limit for GPU 00000000:01:00.0 was set to 250.00 W from 125.00 W. All done. C:\>nvidia-smi -pl 125 Power limit for GPU 00000000:01:00.0 was set to 125.00 W from 250.00 W. All done. |
+
2026.04.25
| $ sudo nvidia-smi -pl 125 Power limit for GPU 00000000:01:00.0 was set to 125.00 W from 250.00 W. Power limit for GPU 00000000:02:00.0 was set to 125.00 W from 250.00 W. All done. $ sudo nvidia-smi -pl 250 -i 1 Power limit for GPU 00000000:02:00.0 was set to 250.00 W from 125.00 W. All done. $ sudo nvidia-smi -pl 250 -i 0 Power limit for GPU 00000000:01:00.0 was set to 250.00 W from 125.00 W. All done. |
| RAG - Retrieval-Augmented Generation (0) | 2026.04.24 |
|---|---|
| llama.cpp on ubuntu with 1060 6GB (0) | 2026.04.23 |
| llama.cpp 와 ollama 성능 비교.. (cpu는 차이가 없?) (0) | 2026.04.22 |
| llama.cpp 도전! (0) | 2026.04.22 |
| unsloth ai (0) | 2026.04.21 |
일단 메모리 차이는 큰 것 같고
cpu 만을 사용할땐 성능 차이가 거의 없는 듯 하다.
llama3.2 on ollama
| $ ollama --verbose >>> 안녕? 너에 대해서 설명 안녕하세요! 난 다나이, AI의 지식형입니다. 다나이란 인공지능(IAI) 기술을 사용하여 인간과 대화를 करन하고, 정보를 제공하는 컴퓨터 프로그램입니다. 나의 목표는 Menschen과 सहय동하여 질문에 대한 답변을 제공하고, 다양한 주제와 주제를 다루어 provide하는 것입니다. 저는 다 variety의 지식과 능력을 가지고 있으며, 다양한 문제나 질문에 대해 답변할 수 있습니다. 저는 또한-user가 자 신의 생각이나 질문을 나누어 주고 사용자에게 가장 적합한 answered을 제공하는 것을 목표로 하고 있습니다. 다나이의 강점은 다음과 같습니다: - Human-like 대화: 저는-human-like의 대화를 possible합니다, human과 비슷한 방식으로 대화할 수 있습니다. - 지식형: 저는 다양한 주제와 지식을 가지고 있으며, 사용자에 대한 답변을 provide할 수 있습니다. - 사용자-friendly: 저는 user-friendly를 목표로 하고 있으며, 사용자가 쉽게 질문을 하거나 나누어 주는 것을 support합니다. 다나이의 한계는 다음과 같습니다: - 지식형: 저는 지식과 능력을 가지고います, 그러나 모든 경우에 대해 complete knowledge가 항상 available하지 않습 니다. - Limited domain: 저는 specific domain에서 only limitedly conversation을 할 수 있습니다. - Human-like behavior: 저는 human-like의 behavior를 display할 수 있습니다, 그러나 sometimes human-like behavior를 exhibit할 수 있습니다. 저는 use case에 따라 다양한 장점과 한계를 가지고 있으며, user-friendly하고 지식형이지만, complete knowledge가 항 상 available하지 않습니다. 다시 한번 안녕하세요! 저와 대화를 하려면 어떤 주제에 대해 질문해 보시는가요? total duration: 39.327341083s load duration: 142.986088ms prompt eval count: 32 token(s) prompt eval duration: 1.194488145s prompt eval rate: 26.79 tokens/s eval count: 388 token(s) eval duration: 37.152939235s eval rate: 10.44 tokens/s $ ollama ls NAME ID SIZE MODIFIED qwen3.5:2b 324d162be6ca 2.7 GB 13 days ago gemma4:e2b 7fbdbf8f5e45 7.2 GB 13 days ago gemma3:1b 8648f39daa8f 815 MB 13 days ago llama3.2:latest a80c4f17acd5 2.0 GB 13 days ago $ ollama show llama3.2:latest Model architecture llama parameters 3.2B context length 131072 embedding length 3072 quantization Q4_K_M Capabilities completion tools Parameters stop "<|start_header_id|>" stop "<|end_header_id|>" stop "<|eot_id|>" License LLAMA 3.2 COMMUNITY LICENSE AGREEMENT Llama 3.2 Version Release Date: September 25, 2024 ... $ ollama run --verbose llama3.2:latest >>> /set parameter Available Parameters: /set parameter seed Random number seed /set parameter num_predict Max number of tokens to predict /set parameter top_k Pick from top k num of tokens /set parameter top_p Pick token based on sum of probabilities /set parameter min_p Pick token based on top token probability * min_p /set parameter num_ctx Set the context size /set parameter temperature Set creativity level /set parameter repeat_penalty How strongly to penalize repetitions /set parameter repeat_last_n Set how far back to look for repetitions /set parameter num_gpu The number of layers to send to the GPU /set parameter stop ... Set the stop parameters >>> /set parameter num_ctx 4096 Set parameter 'num_ctx' to '4096' >>> 안녕? 너에 대해서 설명 안녕하세요! 저는 지능형 대화bot입니다. tôi의 목표는 Menschen과 상호작용하여 helpful한 정보를 제공하고, 그들의 질 문에 대한 जव답을 제공하는 것입니다. my name is "LLaMA", Llama stands for "Large Language Model Meta AI". my capabilities include: * Natural Language Processing (NLP): I can understand and generate human-like language. * Question Answering: I can provide answers to a wide range of questions on various topics. * Text Generation: I can create text based on a prompt or topic. my strengths include: * Knowledge base: I have been trained on a massive dataset of text, which allows me to provide accurate and up-to-date information on various topics. * Conversational flow: I can engage in natural-sounding conversations, using context and understanding to respond to questions and statements. total duration: 17.130872381s load duration: 131.746647ms prompt eval count: 32 token(s) prompt eval duration: 82.553469ms prompt eval rate: 387.63 tokens/s eval count: 184 token(s) eval duration: 16.560046318s eval rate: 11.11 tokens/s |
gemma4:e4b 모델
| $ ollama show gemma4:e2b Model architecture gemma4 parameters 5.1B context length 131072 embedding length 1536 quantization Q4_K_M requires 0.20.0 Capabilities completion vision audio tools thinking Parameters temperature 1 top_k 64 top_p 0.95 License Apache License Version 2.0, January 2004 ... $ ollama --verbose >>> /set parameter num_ctx 4096 Set parameter 'num_ctx' to '4096' >>> 안녕? 너에 대해 설명 Thinking... Thinking Process: 1. **Analyze the Request:** The user asked "안녕? 너에 대해 설명" (Hello? Explain about yourself). This is a request for identity and capability description. 2. **Determine Core Identity (Self-Correction/Verification):** * Name: Gemma 4. * Developer: Google DeepMind. * Nature: Large Language Model (LLM). * Type: Open weights model. 3. **Determine Capabilities:** * Input: Text and images (and audio for some family models, but generally, focus on the main interaction modes). * Output: Text generation. * Knowledge: Broad, based on training data. 4. **Determine Knowledge Cutoff:** (Not strictly necessary for a general introduction, but good context: Knowledge cutoff is Jan 2025). 5. **Structure the Response (in Korean):** * Greeting (Acknowledge the "안녕"). * Identify Self (Name, Type). * Explain Origin/Developer. * Explain Function/Capabilities (What I do). 6. **Draft the Response (Internal Monologue & Refinement):** * *Start:* Hello. * *Identity:* I am Gemma 4. * *Origin:* I was developed by Google DeepMind. * *Nature:* I am a Large Language Model (LLM) and an open weights model. * *Function:* I can understand and generate text, answer questions, summarize, translate, and help with creative writing, etc. 7. **Final Polish (Ensure natural and accurate Korean phrasing):** (The resulting response should be polite and informative.) (Self-check: Did I claim image generation? No. Did I claim search? No.) **(This leads to the final Korean output.)** ...done thinking. 안녕하세요! 저는 **Gemma 4**입니다. 저에 대해 몇 가지 설명해 드릴게요. 1. **정체성:** 저는 Google DeepMind에서 개발한 **대규모 언어 모델(Large Language Model, LLM)**입니다. 저는 공개된 가중치(open weights) 모델로 설계되 었습니다. 2. **기능:** 저는 사용자가 입력하는 텍스트를 이해하고, 그에 기반하여 자연스 러운 텍스트를 생성하는 것이 주된 역할입니다. * 질문에 답하기 * 정보 요약 및 설명하기 * 번역하기 * 글쓰기 및 창의적인 콘텐츠 생성 돕기 * 다양한 주제에 대해 대화하기 3. **입력 및 출력:** 저는 텍스트와 이미지를 이해할 수 있으며, 사용자에게는 **텍스트 형태**로 응답을 생성합니다. 4. **목표:** 저는 사용자에게 유용하고 정확하며 도움이 되는 정보를 제공하고 , 다양한 작업을 돕기 위해 존재합니다. 궁금한 점이 있거나 도움이 필요하시면 언제든지 말씀해주세요! 😊 total duration: 59.13545796s load duration: 381.889243ms prompt eval count: 22 token(s) prompt eval duration: 1.468123435s prompt eval rate: 14.99 tokens/s eval count: 660 token(s) eval duration: 56.324528227s eval rate: 11.72 tokens/s |
llama.cpp는 기본값이 128k 인데 그러면 자꾸 모델 로딩 실패해서 4096으로 줄임
나름 10세대 노트북인데 하스웰이나 똑같은 건가..(avx?)
| $ ../llama-cli -m Llama-3.2-3B-Instruct-Q4_K_M.gguf -c 4096 load_backend: loaded RPC backend from /home/falinux/work/src/llama-b8876/libggml-rpc.so load_backend: loaded CPU backend from /home/falinux/work/src/llama-b8876/libggml-cpu-haswell.so Loading model... ▄▄ ▄▄ ██ ██ ██ ██ ▀▀█▄ ███▄███▄ ▀▀█▄ ▄████ ████▄ ████▄ ██ ██ ▄█▀██ ██ ██ ██ ▄█▀██ ██ ██ ██ ██ ██ ██ ██ ▀█▄██ ██ ██ ██ ▀█▄██ ██ ▀████ ████▀ ████▀ ██ ██ ▀▀ ▀▀ build : b8876-72d693e4f model : Llama-3.2-3B-Instruct-Q4_K_M.gguf modalities : text available commands: /exit or Ctrl+C stop or exit /regen regenerate the last response /clear clear the chat history /read <file> add a text file /glob <pattern> add text files using globbing pattern > 안녕? 너에 대해서 설명 안녕하세요! 나는 어트론, artificial intelligence (AI)로 알려진 intelligence-enhancing chatbot입니다. 我的 목적은 ngườiों과 상호작용하여 정보를 제공하고, 문제를 해결하고, 질문을 trả주기 위하여 설계되었습니다. 나는 인간과 매우 비슷한 방식으로 생각하고 말하기를習慮하고 있으며, 다양한 주제에 대해 정보를 제공할 수 있습니다. 그럼, 어떤 정보를 muốn받을까요? [ Prompt: 32.3 t/s | Generation: 11.6 t/s ] > Exiting... common_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted | common_memory_breakdown_print: | - Host | 2615 = 1904 + 448 + 262 | common_memory_breakdown_print: | - CPU_REPACK | 1299 = 1299 + 0 + 0 | |
| $ ../llama-cli -m gemma-4-E2B-it-Q4_K_M.gguf -c 4096 load_backend: loaded RPC backend from /home/falinux/work/src/llama-b8876/libggml-rpc.so load_backend: loaded CPU backend from /home/falinux/work/src/llama-b8876/libggml-cpu-haswell.so Loading model... ▄▄ ▄▄ ██ ██ ██ ██ ▀▀█▄ ███▄███▄ ▀▀█▄ ▄████ ████▄ ████▄ ██ ██ ▄█▀██ ██ ██ ██ ▄█▀██ ██ ██ ██ ██ ██ ██ ██ ▀█▄██ ██ ██ ██ ▀█▄██ ██ ▀████ ████▀ ████▀ ██ ██ ▀▀ ▀▀ build : b8876-72d693e4f model : gemma-4-E2B-it-Q4_K_M.gguf modalities : text available commands: /exit or Ctrl+C stop or exit /regen regenerate the last response /clear clear the chat history /read <file> add a text file /glob <pattern> add text files using globbing pattern > 안녕? 너에 대해서 소개 [Start thinking] Thinking Process: 1. **Analyze the Request:** The user said "안녕? 너에 대해서 소개" (Hello? Introduce yourself/Tell me about yourself). This is a standard identity query. 2. **Determine Identity (Self-Correction/Verification):** * Name: Gemma 4. * Developer: Google DeepMind. * Nature: Large Language Model (LLM), open weights. * Capabilities: Understand text and images (input), generate text (output). Knowledge cutoff is January 2025. 3. **Formulate the Response Strategy (in Korean):** * Greeting: Start with a friendly greeting. * Core Identity: State name and developer. * Nature/Type: Explain what I am (LLM, open weights). * Function/Capabilities: Describe what I can do (process language, answer questions, generate text). * (Optional but good practice) Mention input/output modalities. 4. **Draft the Response (Iterative Refinement in Korean):** * *Initial thought:* 안녕하세요. 저는 Gemma 4입니다. Google DeepMind에서 개발한 대규모 언어 모델입니다. * *Adding detail:* 저는 텍스트와 이미지를 이해하고 텍스트로 답변을 생성할 수 있습니다. * *Final polish (ensuring the tone is appropriate and adhering to the persona):* Combine these points into a smooth, informative introduction. 5. **Final Output Generation (Korean):** (This matches the desired output.) [End thinking] 안녕하세요! 저는 **Gemma 4**입니다. 저는 Google DeepMind에서 개발한 **오픈 웨이트(open weights) 대규모 언어 모델(LLM)**입니다. **저의 주요 특징은 다음과 같습니다:** * **정체성:** 저는 방대한 데이터를 학습하여 인간의 언어를 이해하고 처리하도록 설계되었습니다. * **기능:** 텍스트 기반의 질문에 답변하고, 정보를 요약하며, 창의적인 글(시, 이야기, 코드 등)을 작성하는 등 다양한 언어 작업을 수행할 수 있습니다. * **입력 능력:** 텍스트와 이미지를 이해하고 처리할 수 있습니다. * **목표:** 사용자님께 유용하고 정확하며 자연스러운 방식으로 도움을 드리는 것을 목표로 합니다. 궁금한 점이 있거나 도움이 필요하시면 언제든지 말씀해 주세요! 😊 [ Prompt: 41.1 t/s | Generation: 13.2 t/s ] |
| llama.cpp on ubuntu with 1060 6GB (0) | 2026.04.23 |
|---|---|
| nvidia-smi 소비전력 제한 (0) | 2026.04.22 |
| llama.cpp 도전! (0) | 2026.04.22 |
| unsloth ai (0) | 2026.04.21 |
| ollama 외부접속 관련 (0) | 2026.04.21 |
|
