biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Attention] FA4 integration (#32974)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson
2026-03-01 18:44:57 -05:00
committed by GitHub
parent 57a96e26c9
commit 8b5014d3dd
15 changed files with 818 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
setup.py
View File

@@ -976,6 +976,11 @@ if _is_cuda():
):
# FA3 requires CUDA 12.3 or later
ext_modules.append(CMakeExtension(name="vllm.vllm_flash_attn._vllm_fa3_C"))
# FA4 CuteDSL - Python-only component for FA4's cute DSL support
# Optional since this doesn't produce a .so file, just copies Python files
ext_modules.append(
CMakeExtension(name="vllm.vllm_flash_attn._vllm_fa4_cutedsl_C", optional=True)
)
if envs.VLLM_USE_PRECOMPILED or (
CUDA_HOME and get_nvcc_cuda_version() >= Version("12.9")
):