biondizzle
72bf750a0b
CUDA graph capture needs extra memory on top of the model weights. With 175GB model on 178GB GPUs, there's no room. Going back to --enforce-eager with 10-min RPC timeout. The first inference request will be slow (2-3 min JIT compilation) but won't crash. Subsequent requests are fast. CUDA graph mode requires either more GPU memory or a smaller model.
31 lines
702 B
YAML
31 lines
702 B
YAML
services:
|
|
vllm:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
ports:
|
|
- "8000:8000"
|
|
environment:
|
|
- OMP_NUM_THREADS=128
|
|
- CUDA_LAUNCH_BLOCKING=0
|
|
- PYTHONUNBUFFERED=1
|
|
- VLLM_RPC_TIMEOUT_MS=600000
|
|
command:
|
|
- /model
|
|
- --trust-remote-code
|
|
- --enable-expert-parallel
|
|
- --tensor-parallel-size=8
|
|
- --enforce-eager
|
|
- --tokenizer-mode=deepseek_v4
|
|
- --host=0.0.0.0
|
|
- --port=8000
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
volumes:
|
|
- /root/nvidia-meeting/DeepSeek-V4-Pro-NVFP4:/model:ro
|