Skip to content

GitLab

Unverified Commit 9c81f35b authored by Matthew Bonanni's avatar Matthew Bonanni Committed by GitHub
Browse files

[Attention][MLA] Re-enable FA4 as default MLA prefill backend (#38819)

parent f186cfe7
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/config/attention.py
View file @ 9c81f35b
...@@ -30,7 +30,7 @@ class AttentionConfig: ...@@ -30,7 +30,7 @@ class AttentionConfig:
use_cudnn_prefill: bool = False use_cudnn_prefill: bool = False
"""Whether to use cudnn prefill.""" """Whether to use cudnn prefill."""
use_trtllm_ragged_deepseek_prefill: bool = True use_trtllm_ragged_deepseek_prefill: bool = False
"""Whether to use TRTLLM ragged deepseek prefill.""" """Whether to use TRTLLM ragged deepseek prefill."""
use_trtllm_attention: bool | None = None use_trtllm_attention: bool | None = None
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment