huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Put back flash-v2 build step.

Browse Source
This commit is contained in:
Nicolas Patry 2024-06-04 13:39:26 +00:00
parent 76fef7b1d2
commit 7c4927482b
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/Makefile-flash-att-v2
View File

@ -1,6 +1,10 @@
flash_att_v2_commit_cuda := v2.5.9.post1
flash_att_v2_commit_rocm := 2554f490101742ccdc56620a938f847f61754be6
build-flash-attention-v2-cuda:
pip install -U packaging wheel
pip install flash-attn==$(flash_att_v2_commit_cuda)
install-flash-attention-v2-cuda:
pip install -U packaging wheel
pip install flash-attn==$(flash_att_v2_commit_cuda)