[Attention] Add trtllm diffusion attention backend with Skip-Softmax (#5283)

Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
This commit is contained in:
SYLARandlishunyang12 authored and GitHub committed 2026-07-27 22:48:11 +08:00
1 parent 4dd1b47f47
commit 7762d664d8
24 files changed
+1512 -52

No files matched your search

+2 -1
View File
@@ -561,7 +561,8 @@ class OmniServeCommand(CLISubcommand):
help="Diffusion attention config. Accepts JSON or vLLM-style dotted flags. "
"Examples: "
"--diffusion-attention-config.default.backend FLASH_ATTN, "
"--diffusion-attention-config.per_role.self.backend SPARSE_BLOCK, "
"--diffusion-attention-config.default.backend TRTLLM_ATTN "
"--diffusion-attention-config.default.skip_softmax.target_sparsity 0.5, "
"--diffusion-attention-config.per_role.cross.backend SAGE_ATTN, "
'--diffusion-attention-config \'{"default": {"backend": "FLASH_ATTN"}, '
'"per_role": {"cross": {"backend": "SAGE_ATTN"}}}\'.',