Model Baichuan2-7B-Chat
| namespace | model name | standby gpu | standby pageable | standby pinned memory | gpu count | vRam (MB) | cpu | memory (MB) | state | revision |
|---|---|---|---|---|---|---|---|---|---|---|
| baichuan-inc | Baichuan2-7B-Chat | Blob | Blob | Blob | 2 | 13800 | 20.0 | 60000 | Normal | 160 |
Image
Prompt
Sample Rest Call
Pods
| tenant | namespace | pod name | state | require resource | allocated resource |
|---|---|---|---|---|---|
| public | baichuan-inc | public/baichuan-inc/Baichuan2-7B-Chat/160/941 | Standby | {'CPU': 20000, 'Mem': 60000, 'GPU': {'Type': 'Any', 'Count': 2, 'vRam': 13800}} | {'nodename': 'node3', 'CPU': 20000, 'Mem': 60000, 'GPUType': 'A4000', 'GPUs': {'vRam': 0, 'map': {}, 'slotSize': 0, 'totalSlotCnt': 0}, 'MaxContextPerGPU': 2} |
Func
| { "image": "vllm/vllm-openai:v0.6.2", "commands": [ "--model", "baichuan-inc/Baichuan2-7B-Chat", "--enforce-eager", "--disable-custom-all-reduce", "--trust-remote-code", "--max-model-len", "1200", "--tensor-parallel-size=2" ], "envs": [ [ "LD_LIBRARY_PATH", "/usr/local/lib/python3.12/dist-packages/nvidia/cuda_nvrtc/lib/:$LD_LIBRARY_PATH" ] ], "mounts": [ { "hostpath": "/home/brad/cache", "mountpath": "/root/.cache/huggingface" } ], "endpoint": { "port": 8000, "schema": "Http", "probe": "/health" }, "version": 160, "entrypoint": [], "resources": { "CPU": 20000, "Mem": 60000, "GPU": { "Type": "Any", "Count": 2, "vRam": 13800 } }, "standby": { "gpu": "Blob", "pageable": "Blob", "pinned": "Blob" }, "probe": { "port": 80, "schema": "Http", "probe": "/health" }, "sample_query": { "apiType": "openai", "path": "v1/completions", "prompt": "\u89e3\u91ca\u4e00\u4e0b'\u6e29\u6545\u800c\u77e5\u65b0'", "body": { "max_tokens": "1000", "model": "baichuan-inc/Baichuan2-7B-Chat", "stream": "true", "temperature": "0" } } } |