ba fongol again4
This commit is contained in:
@@ -17,6 +17,7 @@ services:
|
||||
#- --block-size=256
|
||||
- --enable-expert-parallel
|
||||
- --tensor-parallel-size=8
|
||||
- --enforce-eager
|
||||
#- --compilation-config={"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"]}
|
||||
#- --attention_config.use_fp4_indexer_cache=True
|
||||
- --tokenizer-mode=deepseek_v4
|
||||
|
||||
Reference in New Issue
Block a user