[Attention][MLA] Make FLASHINFER_MLA the default MLA backend on Blackwell, and TRTLLM the default prefill (#32339)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Matthew Bonanni
2026-01-15 09:49:57 -05:00
committed by GitHub
co-authored by Wentao Ye
parent b89275d018
commit 8ebfacaa75
3 changed files with 16 additions and 15 deletions
+1 -1
View File
@@ -35,7 +35,7 @@ class AttentionConfig:
use_cudnn_prefill: bool = False
"""Whether to use cudnn prefill."""
use_trtllm_ragged_deepseek_prefill: bool = False
use_trtllm_ragged_deepseek_prefill: bool = True
"""Whether to use TRTLLM ragged deepseek prefill."""
use_trtllm_attention: bool | None = None