squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[MISC] Keep chunked prefill enabled by default with long context when prefix caching is enabled (#8342)

Browse Source
This commit is contained in:
Cody Yu 2024-09-10 15:28:28 -07:00 committed by GitHub
parent 04e7c4e771
commit b1f3e18958
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/engine/arg_utils.py
View File

@ -878,7 +878,6 @@ class EngineArgs:
if (is_gpu and not use_sliding_window and not use_spec_decode if (is_gpu and not use_sliding_window and not use_spec_decode
and not self.enable_lora and not self.enable_lora
and not self.enable_prompt_adapter and not self.enable_prompt_adapter
and not self.enable_prefix_caching
and not has_seqlen_agnostic_layers): and not has_seqlen_agnostic_layers):
self.enable_chunked_prefill = True self.enable_chunked_prefill = True
logger.warning( logger.warning(