42 lines
1.3 KiB
YAML
42 lines
1.3 KiB
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
|
|
- CLAWMINE_NAN_CHECK=1
|
|
command:
|
|
- /model
|
|
- --trust-remote-code
|
|
- --enable-expert-parallel
|
|
- --tensor-parallel-size=8
|
|
#- --enforce-eager
|
|
- --compilation-config
|
|
#- '{"cudagraph_mode": "NONE", "custom_ops": ["all"]}'
|
|
- '{"cudagraph_mode": "FULL_DECODE_ONLY", "custom_ops": ["all"], "cudagraph_capture_sizes": [1, 2, 4, 8], "max_cudagraph_capture_size": 8}' # This is what is runing right now
|
|
#- '{"cudagraph_mode":"FULL_AND_PIECEWISE", "custom_ops":["all"]}'
|
|
#- --moe-backend=deep_gemm_mega_moe
|
|
- --tokenizer-mode=deepseek_v4
|
|
#- --attention_config.use_fp4_indexer_cache=True
|
|
- --tool-call-parser=deepseek_v4
|
|
- --enable-auto-tool-choice
|
|
- --reasoning-parser=deepseek_v4
|
|
- --gpu_memory_utilization=0.9
|
|
- --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
|