diff --git a/docker-compose.yml b/docker-compose.yml index 51e56fc8..9f37c53e 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -17,17 +17,11 @@ services: - --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 + - --gpu-memory-utilization=0.9 - --host=0.0.0.0 - --port=8000 deploy: