Model llava-1.5-7b-hf
| namespace | model name | standby gpu | standby pageable | standby pinned memory | gpu count | vRam (MB) | cpu | memory (MB) | state | revision |
|---|---|---|---|---|---|---|---|---|---|---|
| llava-hf | llava-1.5-7b-hf | Blob | Blob | Blob | 1 | 14000 | 20.0 | 12000 | Normal | 281 |
Image
Prompt
Sample Rest Call
Pods
| tenant | namespace | pod name | state | require resource | allocated resource |
|---|---|---|---|---|---|
| public | llava-hf | public/llava-hf/llava-1.5-7b-hf/281/952 | Standby | {'CPU': 20000, 'Mem': 12000, 'GPU': {'Type': 'Any', 'Count': 1, 'vRam': 14000}} | {'nodename': 'node3', 'CPU': 20000, 'Mem': 12000, 'GPUType': 'A4000', 'GPUs': {'vRam': 0, 'map': {}, 'slotSize': 0, 'totalSlotCnt': 0}, 'MaxContextPerGPU': 2} |
Func
| { "image": "vllm-openai-upgraded:v0.1.0", "commands": [ "/usr/lib/run_llava.py" ], "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": 281, "entrypoint": [ "/usr/bin/python3" ], "resources": { "CPU": 20000, "Mem": 12000, "GPU": { "Type": "Any", "Count": 1, "vRam": 14000 } }, "standby": { "gpu": "Blob", "pageable": "Blob", "pinned": "Blob" }, "probe": { "port": 80, "schema": "Http", "probe": "/health" }, "sample_query": { "apiType": "llava", "path": "v1/completions", "prompt": "What is shown in this image?", "body": { "image": "https://www.ilankelman.org/stopsigns/australia.jpg" } } } |