fucken a
This commit is contained in:
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user