Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support dedicated compile[For Research] #1384

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

Support dedicated compile[For Research] #1384

wants to merge 2 commits into from

Conversation

AllenDou
Copy link

Support dedicated compile, HEADDIM=64 DTYPE=fp16 ENABLE_SM90=FALSE only build for headdim(64) fp16 and non-sm_90, this method is only for research, could reduce compile time from 50mins -> 5mins.

compile command

MAX_JOBS=8 NVCC_THREADS=2 HEADDIM=64 DTYPE=fp16 ENABLE_SM90=FALSE time pip install -e . -v

run tests

pytest tests/test_flash_attn.py -k test_flash_attn_kvcache -s

support dedicated compile, HEADDIM=64 DTYPE=fp16 ENABLE_SM90=FALSE on…
1705edf 
…ly build for headdim(64) fp16 and non-sm_90.
@AllenDou AllenDou mentioned this pull request Dec 12, 2024
Open
@AllenDou AllenDou marked this pull request as draft December 16, 2024 02:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@AllenDou