Unverified Commit 9c84ca82 authored by Jonas M. Kübler's avatar Jonas M. Kübler Committed by GitHub
Browse files

[FA/Chore] Bump FA version for FP8 two-level accumulation (#27889)


Signed-off-by: default avatarJonas Kuebler <kuebj@amazon.com>
Co-authored-by: default avatarLucas Wilkinson <LucasWilkinson@users.noreply.github.com>
parent 6d54336a
......@@ -38,7 +38,7 @@ else()
FetchContent_Declare(
vllm-flash-attn
GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git
GIT_TAG a893712401d70362fbb299cd9c4b3476e8e9ed54
GIT_TAG 8e1b01d56210dc72030a2d0d41c2d8d266ba6309
GIT_PROGRESS TRUE
# Don't share the vllm-flash-attn build between build types
BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn
......
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