adapt for ModelHub agent platform
This commit is contained in:
CoolBoy
@@ -0,0 +1,53 @@
|
||||
{"templateId": "asr-funasr-iluvatar-bi-150", "taskType": "asr", "framework": "funasr", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: funasr\nlang: zh\nref_config:\n gpu_num: 1\n values:\n command: [python3, main.py, --port, '80', --model_dir, /model, --use_gpu, --model_type,\n sensevoice]\nsut_config:\n gpu_num: 1\n values:\n command: [python3, main.py, --port, '80', --model_dir, /model, --use_gpu, --model_type,\n sensevoice]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 185}}
|
||||
{"templateId": "asr-funasr-iluvatar-mrv-100", "taskType": "asr", "framework": "funasr", "targetGpu": "Iluvatar_mrv-100", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: harbor-contest.4pd.io/sunjichen/funasr:ilu-mr100-service-0.2\nnv_docker_image: harbor-contest.4pd.io/sunjichen/funasr:a100-server-0.2\nframework: funasr\nlang: zh\nsut_config:\n gpu_num: 1\n values:\n command: [python3, main.py, --port, '8000', --model_dir, /model, --model_type,\n paraformer]\nref_config:\n gpu_num: 1\n values:\n command: [python3, main.py, --port, '8000', --model_dir, /model, --model_type,\n paraformer]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 644}}
|
||||
{"templateId": "asr-sherpa-onnx-iluvatar-bi-150", "taskType": "asr", "framework": "sherpa-onnx", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "lang: zh\nframework: sherpa-onnx\nsut_config:\n gpu_num: 1\n values:\n command:\n - python3\n - main_sherpa.py\n - --port\n - '80'\n - --model_dir\n - /model\n - --use_gpu\n - --model_type\n - dolphin_ctc\n - --offline_model\nref_config:\n gpu_num: 1\n values:\n command:\n - python3\n - main_sherpa.py\n - --port\n - '80'\n - --model_dir\n - /model\n - --use_gpu\n - --model_type\n - dolphin_ctc\n - --offline_model\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 193}}
|
||||
{"templateId": "asr-transformers-iluvatar-bi-150", "taskType": "asr", "framework": "transformers", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "lang: zh\nframework: transformers\nsut_config:\n gpu_num: 1\n values:\n command:\n - python3\n - main_transformers.py\n - --port\n - '80'\n - --model_dir\n - /model\n - --use_gpu\nref_config:\n gpu_num: 1\n values:\n command:\n - python3\n - main_transformers.py\n - --port\n - '80'\n - --model_dir\n - /model\n - --use_gpu\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 209}}
|
||||
{"templateId": "feature-emb-sentence-transformers-metax-c-500", "taskType": "feature_emb", "framework": "sentence-transformers", "targetGpu": "MetaX_c-500", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: sentence-transformers\nsut_config:\n gpu_num: 1\n values:\n command:\n - /opt/conda/bin/python\n - -m\n - uvicorn\n - server:app\n - --host\n - 0.0.0.0\n - --port\n - '8000'\nref_config:\n gpu_num: 1\n values:\n command:\n - python3\n - -m\n - uvicorn\n - server:app\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 466}}
|
||||
{"templateId": "question-answering-transformers-iluvatar-bi-150", "taskType": "question_answering", "framework": "transformers", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: transformers\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"torch_dtype\": \"auto\",\n \"handle_impossible_answer\": false,\n \"score_threshold\": 0.0,\n \"max_answer_len\": 30,\n \"max_seq_len\": 512,\n \"doc_stride\": 128\n }\n command:\n - python3\n - main_qa.py\n - --model_dir\n - /model\n - --port\n - '80'\nref_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"torch_dtype\": \"auto\",\n \"handle_impossible_answer\": false,\n \"score_threshold\": 0.0,\n \"max_answer_len\": 30,\n \"max_seq_len\": 512,\n \"doc_stride\": 128\n }\n command:\n - python3\n - main_qa.py\n - --model_dir\n - /model\n - --port\n - '80'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 217}}
|
||||
{"templateId": "reinforcement-learning-llamacpp-iluvatar-bi-150", "taskType": "reinforcement_learning", "framework": "llamacpp", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: llamacpp\napi: completion\nlang: en\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command:\n - /app/llama-server\n - --model\n - /model/Math-Code-Llama3.1-8B.i1-Q4_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\n - --no-mmap\n - --sync-to-temp\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/Math-Code-Llama3.1-8B.i1-Q4_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 225}}
|
||||
{"templateId": "reinforcement-learning-transformers-iluvatar-bi-150", "taskType": "reinforcement_learning", "framework": "transformers", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_DOCKER_IMAGE\napi: completion\nframework: transformers\nnv_framework: vllm\nlang: en\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"model_class\": \"AutoModelForCausalLM\",\n \"torch_dtype\": \"auto\",\n \"model_kwargs\": {\n \"trust_remote_code\": true,\n \"device_map\": \"auto\"\n },\n \"tokenizer_kwargs\": {\n \"use_fast\": true,\n \"trust_remote_code\": true\n },\n \"generate_kwargs\": {\n \"temperature\": 0.01,\n \"top_p\": 0.8,\n \"repetition_penalty\": 1.0,\n \"max_new_tokens\": 1024\n }\n }\n command:\n - python3\n - transformers_server.py\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 233}}
|
||||
{"templateId": "reinforcement-learning-vllm-iluvatar-bi-150", "taskType": "reinforcement_learning", "framework": "vllm", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: git.modelhub.org.cn:9443/enginex-iluvatar-bi150/vllm:0.8.3\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm\napi: completion\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --gpu-memory-utilization\n - '0.9'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 241}}
|
||||
{"templateId": "text-generation-llamacpp-ascend-910-b3", "taskType": "text-generation", "framework": "llamacpp", "targetGpu": "Ascend_910-b3", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_DOCKER_IMAGE\nframework: llamacpp\napi: completion\nmax_tokens: 1024\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build_ascend/bin/llama-server\n - --model\n - /model/Free_Sydney_V2_Mistral_7b.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/Free_Sydney_V2_Mistral_7b.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 41}}
|
||||
{"templateId": "text-generation-llamacpp-ascend-910-b4", "taskType": "text-generation", "framework": "llamacpp", "targetGpu": "Ascend_910-b4", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: llamacpp\napi: chat\nlang: zh\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command: [/workspace/llama.cpp/build_ascend/bin/llama-server, --model, /model/Gemma2-FT-ai-medical-chatbot.Q8_0.gguf,\n --alias, llm, --threads, '16', --n-gpu-layers, '128', --prio, '3', --min_p,\n '0.01', --ctx-size, '4096', --host, 0.0.0.0, --port, '3316', --jinja, --flash-attn,\n 'off']\nref_config:\n gpu_num: 1\n values:\n command: [/workspace/llama.cpp/build/bin/llama-server, --model, /model/Gemma2-FT-ai-medical-chatbot.Q8_0.gguf,\n --alias, llm, --threads, '16', --n-gpu-layers, '128', --prio, '3', --min_p,\n '0.01', --ctx-size, '4096', --host, 0.0.0.0, --port, '80', --jinja]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 73}}
|
||||
{"templateId": "text-generation-llamacpp-iluvatar-bi-150", "taskType": "text-generation", "framework": "llamacpp", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: llamacpp\napi: completion\nlang: en\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command: [/app/llama-server, --model, /model/Math-Code-Llama3.1-8B.i1-Q4_0.gguf,\n --alias, llm, --threads, '20', --n-gpu-layers, '128', --ctx-size, '4096', --host,\n 0.0.0.0, --port, '8000', --jinja, --flash-attn, 'off', --no-mmap, --sync-to-temp]\nref_config:\n gpu_num: 1\n values:\n command: [/workspace/llama.cpp/build/bin/llama-server, --model, /model/Math-Code-Llama3.1-8B.i1-Q4_0.gguf,\n --alias, llm, --threads, '20', --n-gpu-layers, '128', --ctx-size, '4096', --host,\n 0.0.0.0, --port, '8000', --jinja, --flash-attn, 'off']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 547}}
|
||||
{"templateId": "text-generation-llamacpp-mthreads-s4000", "taskType": "text-generation", "framework": "llamacpp", "targetGpu": "Mthreads_s4000", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_DOCKER_IMAGE\nframework: llamacpp\napi: completion\nmax_tokens: 1024\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command:\n - /app/llama-server\n - --model\n - /model/MediQwen-4B.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/MediQwen-4B.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 145}}
|
||||
{"templateId": "text-generation-llamacpp-hygon-k100-ai", "taskType": "text-generation", "framework": "llamacpp", "targetGpu": "hygon_k100-ai", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: llamacpp\ndocker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_NV_DOCKER_IMAGE\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: en\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command: [/app/llama-server, --model, /model/qwen-qwen3-embedding-0.6b-f16.gguf,\n --alias, llm, --threads, '20', --n-gpu-layers, '999', --prio, '3', --min_p,\n '0.01', --ctx-size, '2048', --host, 0.0.0.0, --port, '8000', --jinja, --flash-attn,\n 'off']\nref_config:\n gpu_num: 1\n values:\n command: [/workspace/llama.cpp/build/bin/llama-server, --model, /model/qwen-qwen3-embedding-0.6b-f16.gguf,\n --alias, llm, --threads, '20', --n-gpu-layers, '128', --ctx-size, '4096', --host,\n 0.0.0.0, --port, '8000', --jinja]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 4}}
|
||||
{"templateId": "text-generation-sglang-sunrise-pt-200-x1", "taskType": "text-generation", "framework": "sglang", "targetGpu": "Sunrise_pt-200-x1", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: git.modelhub.org.cn:9443/enginex-sunrise/sglang:0.4.6.post2\nnv_docker_image: harbor.4pd.io/hardcore-tech/public/sglang:v0.5.8\nframework: sglang\napi: completion\nlang: en\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n values:\n command: [python3.10, -m, sglang.launch_server, --model-path, /model, --port,\n '17097', --served-model-name, llm, --context-length, '4096', --trust-remote-code,\n --host, 0.0.0.0, --disable-cuda-graph, --disable-radix-cache]\nref_config:\n gpu_num: 1\n values:\n command: [python3, -m, sglang.launch_server, --model-path, /model, --port, '8000',\n --served-model-name, llm, --context-length, '4096', --trust-remote-code, --host,\n 0.0.0.0]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 442}}
|
||||
{"templateId": "text-generation-transformers-iluvatar-bi-100", "taskType": "text-generation", "framework": "transformers", "targetGpu": "Iluvatar_bi-100", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: harbor-contest.4pd.io/sunjichen/funasr:ilu-mr100-service-0.2\nnv_docker_image: harbor-contest.4pd.io/sunjichen/funasr:a100-server-0.2\napi: completion\nframework: transformers\nnv_framework: vllm\nlang: en\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"model_class\": \"AutoModelForCausalLM\",\n \"torch_dtype\": \"auto\",\n \"model_kwargs\": {\n \"trust_remote_code\": true,\n \"device_map\": \"auto\"\n },\n \"tokenizer_kwargs\": {\n \"use_fast\": true,\n \"trust_remote_code\": true\n },\n \"generate_kwargs\": {\n \"temperature\": 0.01,\n \"top_p\": 0.8,\n \"repetition_penalty\": 1.0,\n \"max_new_tokens\": 1024\n }\n }\n command: [python3, transformers_server.py]\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --enforce-eager, --trust-remote-code, -tp, '1']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 612}}
|
||||
{"templateId": "text-generation-transformers-iluvatar-bi-150", "taskType": "text-generation", "framework": "transformers", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_DOCKER_IMAGE\napi: completion\nframework: transformers\nnv_framework: vllm\nlang: en\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"model_class\": \"AutoModelForCausalLM\",\n \"torch_dtype\": \"auto\",\n \"model_kwargs\": {\n \"trust_remote_code\": true,\n \"device_map\": \"auto\"\n },\n \"tokenizer_kwargs\": {\n \"use_fast\": true,\n \"trust_remote_code\": true\n },\n \"generate_kwargs\": {\n \"temperature\": 0.01,\n \"top_p\": 0.8,\n \"repetition_penalty\": 1.0,\n \"max_new_tokens\": 1024\n }\n }\n command:\n - python3\n - transformers_server.py\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 555}}
|
||||
{"templateId": "text-generation-transformers-iluvatar-mrv-100", "taskType": "text-generation", "framework": "transformers", "targetGpu": "Iluvatar_mrv-100", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: harbor-contest.4pd.io/sunjichen/funasr:ilu-mr100-service-0.2\nnv_docker_image: harbor-contest.4pd.io/sunjichen/funasr:a100-server-0.2\napi: completion\nframework: transformers\nnv_framework: vllm\nlang: en\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"model_class\": \"AutoModelForCausalLM\",\n \"torch_dtype\": \"auto\",\n \"model_kwargs\": {\n \"trust_remote_code\": true,\n \"device_map\": \"auto\"\n },\n \"tokenizer_kwargs\": {\n \"use_fast\": true,\n \"trust_remote_code\": true\n },\n \"generate_kwargs\": {\n \"temperature\": 0.01,\n \"top_p\": 0.8,\n \"repetition_penalty\": 1.0,\n \"max_new_tokens\": 1024\n }\n }\n command: [python3, transformers_server.py]\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --enforce-eager, --trust-remote-code, -tp, '1']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 653}}
|
||||
{"templateId": "text-generation-vllm-ascend-910-b3", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Ascend_910-b3", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_DOCKER_IMAGE\nframework: vllm\napi: completion\nlang: en\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '20644'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 49}}
|
||||
{"templateId": "text-generation-vllm-ascend-910-b4", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Ascend_910-b4", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm\ndocker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_NV_DOCKER_IMAGE\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: zh\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --dtype\n - auto\n - --gpu-memory-utilization\n - '0.95'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --dtype\n - auto\n - --gpu-memory-utilization\n - '0.95'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 81}}
|
||||
{"templateId": "text-generation-vllm-biren-166m", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Biren_166m", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm\ndocker_image: git.modelhub.org.cn:9443/enginex/xc-llm-biren166m:26.01\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: zh\nmax_model_len: 4096\nsut_config:\n gpu_num: 4\n values:\n command: [/bin/bash, -ic, vllm serve /model --port 8000 --served-model-name llm\n --max-model-len 4096 --dtype auto --gpu-memory-utilization 0.9 --enforce-eager\n --trust-remote-code -tp 4 --host 0.0.0.0]\nref_config:\n gpu_num: 4\n values:\n command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len,\n '4096', --dtype, auto, --gpu-memory-utilization, '0.95', -tp, '4', --enforce-eager,\n --trust-remote-code]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 137}}
|
||||
{"templateId": "text-generation-vllm-cambricon-mlu-370-x4", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Cambricon_mlu-370-x4", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: harbor.4pd.io/hardcore-tech/cambricon-mlu370-pytorch:v25.01-torch2.5.0-torchmlu1.24.1-ubuntu22.04-py310\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm\nsut_config:\n values:\n gpu_num: 1\n env:\n - {name: MAX_MODEL_LEN, value: 4096}\n command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len,\n '4096', --trust-remote-code, --dtype, float16]\nref_config:\n values:\n cpu_num: 2\n gpu_num: 1\n env:\n - {name: MAX_MODEL_LEN, value: 4096}\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --trust-remote-code, --dtype, float16]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 361}}
|
||||
{"templateId": "text-generation-vllm-iluvatar-bi-100", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Iluvatar_bi-100", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm\nlang: en\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command: [/workspace/launch_service, --port, '80']\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --enforce-eager, --trust-remote-code, -tp, '1']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 620}}
|
||||
{"templateId": "text-generation-vllm-iluvatar-bi-150", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: git.modelhub.org.cn:9443/enginex-iluvatar-bi150/vllm:0.8.3\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm\napi: completion\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --gpu-memory-utilization, '0.9', --enforce-eager, --trust-remote-code,\n -tp, '1']\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --enforce-eager, --trust-remote-code, -tp, '1']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 563}}
|
||||
{"templateId": "text-generation-vllm-iluvatar-mrv-100", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Iluvatar_mrv-100", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: harbor.4pd.io/hardcore-tech/iluvatar/llm-infer-iluvatar-mr:v0\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm\nmax_model_len: 4096\nlang: en\ntemperature: 0.4\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '20644', --served-model-name, llm, --max-model-len,\n '4096', --gpu-memory-utilization, '0.9', --enforce-eager, --trust-remote-code,\n -tp, '1']\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --enforce-eager, --trust-remote-code, -tp, '1']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 661}}
|
||||
{"templateId": "text-generation-vllm-kunlunxin-p-800", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Kunlunxin_p-800", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm\ndocker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_NV_DOCKER_IMAGE\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: zh\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len,\n '2048', --dtype, auto, --gpu-memory-utilization, '0.95', -tp, '1', --enforce-eager,\n --trust-remote-code]\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len,\n '2048', --dtype, auto, --gpu-memory-utilization, '0.95', -tp, '1', --enforce-eager,\n --trust-remote-code]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 177}}
|
||||
{"templateId": "text-generation-vllm-kunlunxin-r-200-8f", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Kunlunxin_r-200-8f", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: harbor.4pd.io/mic-llm-x/slx-infer-kunlunxin:release-0.1-pipe-6-commit-f2eb860f\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm\nmax_model_len: 4096\napi: completion\nsut_config:\n gpu_num: 1\n values:\n command: [sh, -c, rm -rf /workspace/xtrt_engine/fp16-1xpu && mkdir -p /workspace/xtrt_engine/fp16-1xpu\n && python3 examples/qwen/build.py --hf_model_dir /model --output_dir /workspace/xtrt_engine/fp16-1xpu\n --dtype float16 --use_gpt_attention_plugin float16 --world_size 1 --tp_size\n 1 --remove_input_padding --opt_memory_use --paged_kv_cache --tokens_per_block\n 64 --version 1.5 && exec python3 -m xtrt_llm.vllm.entrypoints.openai.api_server\n --model /model --engine_dir /workspace/xtrt_engine/fp16-1xpu --port 8000 --served-model-name\n llm --max-model-len 4096 --trust-remote-code --dtype float16]\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --enforce-eager, --trust-remote-code, -tp, '1']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 434}}
|
||||
{"templateId": "text-generation-vllm-metax-c-500", "taskType": "text-generation", "framework": "vllm", "targetGpu": "MetaX_c-500", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: git.modelhub.org.cn:9443/enginex-metax/vllm:0.9.1\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm\napi: completion\nlang: en\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command: [/opt/conda/bin/vllm, serve, /model, --port, '20644', --served-model-name,\n llm, --max-model-len, '4096', --gpu-memory-utilization, '0.9', -tp, '1', --enforce-eager,\n --trust-remote-code]\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', -tp, '1', --enforce-eager, --trust-remote-code]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 475}}
|
||||
{"templateId": "text-generation-vllm-mthreads-s4000", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Mthreads_s4000", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_DOCKER_IMAGE\nframework: vllm\napi: completion\nlang: en\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --dtype\n - auto\n - --gpu-memory-utilization\n - '0.95'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --dtype\n - auto\n - --gpu-memory-utilization\n - '0.95'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 153}}
|
||||
{"templateId": "text-generation-vllm-sunrise-pt-200-x1", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Sunrise_pt-200-x1", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "api: completion\nframework: vllm\nmax_model_len: 4096\nmax_tokens: 1024\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len,\n '4096', --trust-remote-code, --host, 0.0.0.0, --enforce-eager]\n env:\n - {name: VLLM_ALLOW_LONG_MAX_MODEL_LEN, value: 1}\nsut_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '17097', --served-model-name, llm, --max-model-len,\n '4096', --trust-remote-code, --host, 0.0.0.0, --enforce-eager]\n env:\n - {name: VLLM_ALLOW_LONG_MAX_MODEL_LEN, value: 1}\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 450}}
|
||||
{"templateId": "text-generation-vllm-vastai-va16", "taskType": "text-generation", "framework": "vllm", "targetGpu": "Vastai_va16", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-va16:26.03\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm\napi: completion\nlang: zh\nmax_model_len: 2048\nsut_config:\n values:\n gpu_num: 1\n env:\n - {name: MAX_MODEL_LEN, value: 2048}\n command: [/bin/bash, -ic, vllm serve /model --port 8000 --served-model-name llm\n --max-model-len 2048 --gpu-memory-utilization 0.9 --enforce-eager --trust-remote-code\n -tp 1 --host 0.0.0.0]\nref_config:\n values:\n cpu_num: 2\n gpu_num: 1\n env:\n - {name: MAX_MODEL_LEN, value: 2048}\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '2048', --enforce-eager, --trust-remote-code, -tp, '1']\nmodel: llm\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 249}}
|
||||
{"templateId": "text-generation-vllm-hygon-k100-ai", "taskType": "text-generation", "framework": "vllm", "targetGpu": "hygon_k100-ai", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: git.modelhub.org.cn:9443/enginex-hygon/vllm:0.9.2\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm\nmax_model_len: 4096\napi: completion\nsut_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '20644', --served-model-name, llm, --max-model-len,\n '4096', --enforce-eager, --trust-remote-code, -tp, '1']\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --enforce-eager, --trust-remote-code, -tp, '1']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 12}}
|
||||
{"templateId": "text-generation-vllm-016-iluvatar-bi-150", "taskType": "text-generation", "framework": "vllm-016", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm-016\nlang: en\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 571}}
|
||||
{"templateId": "text-generation-vllm-customized-cambricon-mlu-370-x4", "taskType": "text-generation", "framework": "vllm-customized", "targetGpu": "Cambricon_mlu-370-x4", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: harbor.4pd.io/hardcore-tech/cambricon-mlu370-pytorch:v25.01-20260204\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm-customized\napi: completion\nlang: en\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len,\n '4096', --dtype, half, --gpu-memory-utilization, '0.95', -tp, '1', --enforce-eager,\n --trust-remote-code]\nref_config:\n gpu_num: 1\n values:\n command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len,\n '4096', --dtype, auto, --gpu-memory-utilization, '0.95', -tp, '1', --enforce-eager,\n --trust-remote-code]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 369}}
|
||||
{"templateId": "text-generation-vllm-mlu-cambricon-mlu-370-x4", "taskType": "text-generation", "framework": "vllm-mlu", "targetGpu": "Cambricon_mlu-370-x4", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: harbor.4pd.io/hardcore-tech/cambricon-mlu370-pytorch:v25.01-torch2.5.0-torchmlu1.24.1-ubuntu22.04-py310\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm-mlu\nsut_config:\n values:\n gpu_num: 1\n env:\n - {name: MAX_MODEL_LEN, value: 4096}\n command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len,\n '4096', --trust-remote-code, --dtype, float16]\nref_config:\n values:\n cpu_num: 2\n gpu_num: 1\n env:\n - {name: MAX_MODEL_LEN, value: 4096}\n command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len,\n '4096', --trust-remote-code, --dtype, float16]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 377}}
|
||||
{"templateId": "text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1", "taskType": "text-generation", "framework": "vllm_fix_tokenizer", "targetGpu": "Sunrise_pt-200-x1", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm_fix_tokenizer\ndocker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_NV_DOCKER_IMAGE\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: zh\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command: [/opt/entrypoint.sh, /model, --port, '8000', --served-model-name, llm,\n --max-model-len, '4096', --gpu-memory-utilization, '0.9', --enforce-eager, --trust-remote-code]\nref_config:\n gpu_num: 1\n values:\n command: [/opt/entrypoint.sh, /model, --port, '8000', --served-model-name, llm,\n --max-model-len, '4096', --dtype, float16, --gpu-memory-utilization, '0.95',\n -tp, '1', --enforce-eager, --trust-remote-code]\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 458}}
|
||||
{"templateId": "text-to-image-generation-diffusers-iluvatar-bi-100", "taskType": "text-to-image-generation", "framework": "diffusers", "targetGpu": "Iluvatar_bi-100", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: harbor-contest.4pd.io/zhanghao/t2i:bi100-v0.3\nnv_docker_image: harbor-contest.4pd.io/zhanghao/t2i:a100-v0.3\nframework: diffusers\nsut_config:\n gpu_num: 1\n values:\n env:\n - {name: DTYPE, value: fp16}\n command: [/workspace/entrypoint.sh, --port, '80']\nref_config:\n gpu_num: 1\n values:\n env:\n - {name: DTYPE, value: fp16}\n command: [/workspace/entrypoint.sh, --port, '80']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 628}}
|
||||
{"templateId": "text-to-image-generation-diffusers-iluvatar-bi-150", "taskType": "text-to-image-generation", "framework": "diffusers", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: diffusers\nsut_config:\n values:\n gpu_num: 1\n env:\n - {name: DTYPE, value: fp16}\n command: [/workspace/entrypoint.sh, --port, '80']\nref_config:\n values:\n gpu_num: 1\n env:\n - {name: DTYPE, value: fp16}\n command: [/workspace/entrypoint.sh, --port, '80']\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 580}}
|
||||
{"templateId": "text-to-image-generation-diffusers-iluvatar-mrv-100", "taskType": "text-to-image-generation", "framework": "diffusers", "targetGpu": "Iluvatar_mrv-100", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: diffusers\nsut_config:\n values:\n gpu_num: 1\n env:\n - name: DTYPE\n value: fp16\n command:\n - /workspace/entrypoint.sh\n - --port\n - '80'\nref_config:\n values:\n gpu_num: 1\n env:\n - name: DTYPE\n value: fp16\n command:\n - /workspace/entrypoint.sh\n - --port\n - '80'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 669}}
|
||||
{"templateId": "text-classification-transformers-iluvatar-bi-150", "taskType": "text_classification", "framework": "transformers", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "classification_type: sentiment/emotion/toxicity/hate (根据文本分类的任务类型四选一)\nframework: transformers\nnv_framework: transformers\nmodelhub_options:\n srcRelativePath: leaderboard/modelHubXC/nlptown/bert-base-multilingual-uncased-sentiment\n mountPoint: /model\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"model_class\": \"AutoModelForSequenceClassification\",\n \"tokenizer_class\": \"AutoTokenizer\",\n \"torch_dtype\": \"auto\"\n }\n command:\n - python3\n - transformers_server.py\nref_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"model_class\": \"AutoModelForSequenceClassification\",\n \"tokenizer_class\": \"AutoTokenizer\",\n \"torch_dtype\": \"auto\"\n }\n command:\n - python3\n - transformers_server.py\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 588}}
|
||||
{"templateId": "vision-classification-transformers-iluvatar-bi-150", "taskType": "vision_classification", "framework": "transformers", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: transformers\nnv_framework: transformers\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"model_class\": \"AutoModelForImageClassification\",\n \"processer_class\": \"AutoImageProcessor\",\n \"torch_dtype\": \"auto\"\n }\n command:\n - python3\n - transformers_server.py\nref_config:\n gpu_num: 1\n values:\n env:\n - name: CONFIG_JSON\n value: |\n {\n \"model_class\": \"AutoModelForImageClassification\",\n \"processer_class\": \"AutoImageProcessor\",\n \"torch_dtype\": \"auto\"\n }\n command:\n - python3\n - transformers_server.py\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 596}}
|
||||
{"templateId": "visual-multi-modal-llamacpp-ascend-910-b3", "taskType": "visual-multi-modal", "framework": "llamacpp", "targetGpu": "Ascend_910-b3", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_DOCKER_IMAGE\nframework: llamacpp\napi: completion\nmax_tokens: 1024\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build_ascend/bin/llama-server\n - --model\n - /model/Free_Sydney_V2_Mistral_7b.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/Free_Sydney_V2_Mistral_7b.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 57}}
|
||||
{"templateId": "visual-multi-modal-llamacpp-ascend-910-b4", "taskType": "visual-multi-modal", "framework": "llamacpp", "targetGpu": "Ascend_910-b4", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: llamacpp\napi: chat\nlang: zh\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build_ascend/bin/llama-server\n - --model\n - /model/Gemma2-FT-ai-medical-chatbot.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '16'\n - --n-gpu-layers\n - '128'\n - --prio\n - '3'\n - --min_p\n - '0.01'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '3316'\n - --jinja\n - --flash-attn\n - 'off'\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/Gemma2-FT-ai-medical-chatbot.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '16'\n - --n-gpu-layers\n - '128'\n - --prio\n - '3'\n - --min_p\n - '0.01'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '80'\n - --jinja\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 89}}
|
||||
{"templateId": "visual-multi-modal-llamacpp-mthreads-s4000", "taskType": "visual-multi-modal", "framework": "llamacpp", "targetGpu": "Mthreads_s4000", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: llamacpp\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command:\n - /app/llama-server\n - --model\n - /model/glm-4-9b-chat-1m.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/glm-4-9b-chat-1m.Q8_0.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 161}}
|
||||
{"templateId": "visual-multi-modal-llamacpp-hygon-k100-ai", "taskType": "visual-multi-modal", "framework": "llamacpp", "targetGpu": "hygon_k100-ai", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: llamacpp\nmax_model_len: 1024\nsut_config:\n gpu_num: 1\n values:\n command:\n - /app/llama-server\n - --model\n - /model/Qwen3-14B-BF16.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/Qwen3-14B-BF16.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 22}}
|
||||
{"templateId": "visual-multi-modal-vllm-ascend-910-b3", "taskType": "visual-multi-modal", "framework": "vllm", "targetGpu": "Ascend_910-b3", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_DOCKER_IMAGE\nframework: vllm\napi: completion\nlang: en\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '20644'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 65}}
|
||||
{"templateId": "visual-multi-modal-vllm-ascend-910-b4", "taskType": "visual-multi-modal", "framework": "vllm", "targetGpu": "Ascend_910-b4", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm\ndocker_image: PLACEHOLDER_DOCKER_IMAGE\nnv_docker_image: PLACEHOLDER_NV_DOCKER_IMAGE\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: zh\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --dtype\n - auto\n - --gpu-memory-utilization\n - '0.95'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --dtype\n - auto\n - --gpu-memory-utilization\n - '0.95'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 97}}
|
||||
{"templateId": "visual-multi-modal-vllm-iluvatar-bi-100", "taskType": "visual-multi-modal", "framework": "vllm", "targetGpu": "Iluvatar_bi-100", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: SERVED_MODEL_NAME\n value: vlm\n command:\n - /workspace/launch_service\n - --port\n - '80'\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - vlm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 636}}
|
||||
{"templateId": "visual-multi-modal-vllm-iluvatar-bi-150", "taskType": "visual-multi-modal", "framework": "vllm", "targetGpu": "Iluvatar_bi-150", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "docker_image: git.modelhub.org.cn:9443/enginex-iluvatar-bi150/vllm:0.8.3\nnv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0\nframework: vllm\napi: completion\nmax_model_len: 4096\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --gpu-memory-utilization\n - '0.9'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 604}}
|
||||
{"templateId": "visual-multi-modal-vllm-iluvatar-mrv-100", "taskType": "visual-multi-modal", "framework": "vllm", "targetGpu": "Iluvatar_mrv-100", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: SERVED_MODEL_NAME\n value: vlm\n command:\n - /workspace/launch_service\n - --port\n - '80'\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - vlm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 677}}
|
||||
{"templateId": "visual-multi-modal-vllm-metax-c-500", "taskType": "visual-multi-modal", "framework": "vllm", "targetGpu": "MetaX_c-500", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm\nnv_framework: vllm_v10\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command:\n - /opt/conda/bin/vllm\n - serve\n - /model\n - --port\n - '8898'\n - --served-model-name\n - vlm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - vlm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 483}}
|
||||
{"templateId": "visual-multi-modal-vllm-mthreads-s4000", "taskType": "visual-multi-modal", "framework": "vllm", "targetGpu": "Mthreads_s4000", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framewok: vllm\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --served-model-name\n - llm\n - --trust-remote-code\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --gpu-memory-utilization\n - '0.5'\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --served-model-name\n - llm\n - --trust-remote-code\n - --max-model-len\n - '4096'\n - --enforce-eager\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 169}}
|
||||
{"templateId": "visual-multi-modal-vllm-hygon-k100-ai", "taskType": "visual-multi-modal", "framework": "vllm", "targetGpu": "hygon_k100-ai", "modelAddressTemplate": "{{MODEL_ADDRESS}}", "sampleModelAddress": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "configParams": "framework: vllm\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '20644'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\nref_config:\n gpu_num: 1\n values:\n command:\n - vllm\n - serve\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '4096'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\n", "source": {"file": "/modelHub/网页版提交抓包样例.md", "line": 31}}
|
||||
279
modelhub_submmit_api/templates/public_submit/template_index.json
Normal file
279
modelhub_submmit_api/templates/public_submit/template_index.json
Normal file
@@ -0,0 +1,279 @@
|
||||
{
|
||||
"sourceFile": "/modelHub/网页版提交抓包样例.md",
|
||||
"totalExtractedSamples": 84,
|
||||
"totalUniqueTemplates": 53,
|
||||
"taskTypes": {
|
||||
"asr": {
|
||||
"funasr": [
|
||||
{
|
||||
"templateId": "asr-funasr-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
},
|
||||
{
|
||||
"templateId": "asr-funasr-iluvatar-mrv-100",
|
||||
"targetGpu": "Iluvatar_mrv-100"
|
||||
}
|
||||
],
|
||||
"sherpa-onnx": [
|
||||
{
|
||||
"templateId": "asr-sherpa-onnx-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
}
|
||||
],
|
||||
"transformers": [
|
||||
{
|
||||
"templateId": "asr-transformers-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
}
|
||||
]
|
||||
},
|
||||
"feature_emb": {
|
||||
"sentence-transformers": [
|
||||
{
|
||||
"templateId": "feature-emb-sentence-transformers-metax-c-500",
|
||||
"targetGpu": "MetaX_c-500"
|
||||
}
|
||||
]
|
||||
},
|
||||
"question_answering": {
|
||||
"transformers": [
|
||||
{
|
||||
"templateId": "question-answering-transformers-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
}
|
||||
]
|
||||
},
|
||||
"reinforcement_learning": {
|
||||
"llamacpp": [
|
||||
{
|
||||
"templateId": "reinforcement-learning-llamacpp-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
}
|
||||
],
|
||||
"transformers": [
|
||||
{
|
||||
"templateId": "reinforcement-learning-transformers-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
}
|
||||
],
|
||||
"vllm": [
|
||||
{
|
||||
"templateId": "reinforcement-learning-vllm-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
}
|
||||
]
|
||||
},
|
||||
"text-generation": {
|
||||
"llamacpp": [
|
||||
{
|
||||
"templateId": "text-generation-llamacpp-ascend-910-b3",
|
||||
"targetGpu": "Ascend_910-b3"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-llamacpp-ascend-910-b4",
|
||||
"targetGpu": "Ascend_910-b4"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-llamacpp-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-llamacpp-mthreads-s4000",
|
||||
"targetGpu": "Mthreads_s4000"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-llamacpp-hygon-k100-ai",
|
||||
"targetGpu": "hygon_k100-ai"
|
||||
}
|
||||
],
|
||||
"sglang": [
|
||||
{
|
||||
"templateId": "text-generation-sglang-sunrise-pt-200-x1",
|
||||
"targetGpu": "Sunrise_pt-200-x1"
|
||||
}
|
||||
],
|
||||
"transformers": [
|
||||
{
|
||||
"templateId": "text-generation-transformers-iluvatar-bi-100",
|
||||
"targetGpu": "Iluvatar_bi-100"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-transformers-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-transformers-iluvatar-mrv-100",
|
||||
"targetGpu": "Iluvatar_mrv-100"
|
||||
}
|
||||
],
|
||||
"vllm": [
|
||||
{
|
||||
"templateId": "text-generation-vllm-ascend-910-b3",
|
||||
"targetGpu": "Ascend_910-b3"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-ascend-910-b4",
|
||||
"targetGpu": "Ascend_910-b4"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-biren-166m",
|
||||
"targetGpu": "Biren_166m"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-cambricon-mlu-370-x4",
|
||||
"targetGpu": "Cambricon_mlu-370-x4"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-iluvatar-bi-100",
|
||||
"targetGpu": "Iluvatar_bi-100"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-iluvatar-mrv-100",
|
||||
"targetGpu": "Iluvatar_mrv-100"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-kunlunxin-p-800",
|
||||
"targetGpu": "Kunlunxin_p-800"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-kunlunxin-r-200-8f",
|
||||
"targetGpu": "Kunlunxin_r-200-8f"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-metax-c-500",
|
||||
"targetGpu": "MetaX_c-500"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-mthreads-s4000",
|
||||
"targetGpu": "Mthreads_s4000"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-sunrise-pt-200-x1",
|
||||
"targetGpu": "Sunrise_pt-200-x1"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-vastai-va16",
|
||||
"targetGpu": "Vastai_va16"
|
||||
},
|
||||
{
|
||||
"templateId": "text-generation-vllm-hygon-k100-ai",
|
||||
"targetGpu": "hygon_k100-ai"
|
||||
}
|
||||
],
|
||||
"vllm-016": [
|
||||
{
|
||||
"templateId": "text-generation-vllm-016-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
}
|
||||
],
|
||||
"vllm-customized": [
|
||||
{
|
||||
"templateId": "text-generation-vllm-customized-cambricon-mlu-370-x4",
|
||||
"targetGpu": "Cambricon_mlu-370-x4"
|
||||
}
|
||||
],
|
||||
"vllm-mlu": [
|
||||
{
|
||||
"templateId": "text-generation-vllm-mlu-cambricon-mlu-370-x4",
|
||||
"targetGpu": "Cambricon_mlu-370-x4"
|
||||
}
|
||||
],
|
||||
"vllm_fix_tokenizer": [
|
||||
{
|
||||
"templateId": "text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1",
|
||||
"targetGpu": "Sunrise_pt-200-x1"
|
||||
}
|
||||
]
|
||||
},
|
||||
"text-to-image-generation": {
|
||||
"diffusers": [
|
||||
{
|
||||
"templateId": "text-to-image-generation-diffusers-iluvatar-bi-100",
|
||||
"targetGpu": "Iluvatar_bi-100"
|
||||
},
|
||||
{
|
||||
"templateId": "text-to-image-generation-diffusers-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
},
|
||||
{
|
||||
"templateId": "text-to-image-generation-diffusers-iluvatar-mrv-100",
|
||||
"targetGpu": "Iluvatar_mrv-100"
|
||||
}
|
||||
]
|
||||
},
|
||||
"text_classification": {
|
||||
"transformers": [
|
||||
{
|
||||
"templateId": "text-classification-transformers-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
}
|
||||
]
|
||||
},
|
||||
"vision_classification": {
|
||||
"transformers": [
|
||||
{
|
||||
"templateId": "vision-classification-transformers-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
}
|
||||
]
|
||||
},
|
||||
"visual-multi-modal": {
|
||||
"llamacpp": [
|
||||
{
|
||||
"templateId": "visual-multi-modal-llamacpp-ascend-910-b3",
|
||||
"targetGpu": "Ascend_910-b3"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-llamacpp-ascend-910-b4",
|
||||
"targetGpu": "Ascend_910-b4"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-llamacpp-mthreads-s4000",
|
||||
"targetGpu": "Mthreads_s4000"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-llamacpp-hygon-k100-ai",
|
||||
"targetGpu": "hygon_k100-ai"
|
||||
}
|
||||
],
|
||||
"vllm": [
|
||||
{
|
||||
"templateId": "visual-multi-modal-vllm-ascend-910-b3",
|
||||
"targetGpu": "Ascend_910-b3"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-vllm-ascend-910-b4",
|
||||
"targetGpu": "Ascend_910-b4"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-vllm-iluvatar-bi-100",
|
||||
"targetGpu": "Iluvatar_bi-100"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-vllm-iluvatar-bi-150",
|
||||
"targetGpu": "Iluvatar_bi-150"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-vllm-iluvatar-mrv-100",
|
||||
"targetGpu": "Iluvatar_mrv-100"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-vllm-metax-c-500",
|
||||
"targetGpu": "MetaX_c-500"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-vllm-mthreads-s4000",
|
||||
"targetGpu": "Mthreads_s4000"
|
||||
},
|
||||
{
|
||||
"templateId": "visual-multi-modal-vllm-hygon-k100-ai",
|
||||
"targetGpu": "hygon_k100-ai"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user