iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI] Bump CUTLASS DSL to 4.7 (#54927)

Browse Source 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Codex <codex@openai.com>
This commit is contained in:
Jiangyun Zhu
2026-09-11 20:11:29 -07:00
committed by GitHub
co-authored by Codex
parent 31759ccb6d
commit ec6b0494fe
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmake/external_projects/tml_fa4.cmake
+1 -1
View File
@@ -14,7 +14,7 @@ else()
FetchContent_Declare(
tml_fa4
GIT_REPOSITORY https://github.com/vllm-project/tml-fa4.git
GIT_TAG b206834606ed5b5f21f8eed6b0683f528ea9cf7d
GIT_TAG 75765e76a9c2c012c1f6ecd64577eb646eb4d303
GIT_PROGRESS TRUE
CONFIGURE_COMMAND ""
BUILD_COMMAND "")
requirements/cuda.txt
+2 -2
View File
@@ -26,8 +26,8 @@ fastsafetensors >= 0.3.3
instanttensor >= 0.1.9
# QuACK and Cutlass DSL for FA4 (cute-DSL implementation)
nvidia-cutlass-dsl[cu13]==4.6.2
quack-kernels==0.6.4 # Required for CUTLASS DSL 4.6 by MSA
nvidia-cutlass-dsl[cu13]==4.7.1
quack-kernels==0.6.5 # Required by MSA
# Tokenspeed_MLA for faster mla with spec decode
tokenspeed-mla==0.1.8; platform_system == "Linux"