This commit is contained in:
2026-05-16 08:23:27 +00:00
parent 72bf750a0b
commit a51ef3d2cf

View File

@@ -15,7 +15,8 @@ services:
- --trust-remote-code
- --enable-expert-parallel
- --tensor-parallel-size=8
- --enforce-eager
- --compilation-config
- '{"cudagraph_mode": "FULL_DECODE_ONLY", "custom_ops": ["all"], "cudagraph_capture_sizes": [1, 2, 4, 8], "max_cudagraph_capture_size": 8}'
- --tokenizer-mode=deepseek_v4
- --host=0.0.0.0
- --port=8000