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.

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

[FIX] GPU detection in multigpu env and OEM A100 not matching TVM #58

Merged
merged 1 commit into from
Jun 21, 2024

Conversation

Qubitium
Copy link
Contributor

@Qubitium Qubitium commented Jun 21, 2024

There are two bug fixes in this PR

  1. In a multipe gpu setup, [CORE] Add Bitblas Format/Kernel Support ModelCloud/GPTQModel#39 may need to execute on a single gpu in a multi-gpu env where the gpu_id is not 0 according to nvidia-smi. The current setup assume TVM target is always the first gpu (index=0) which is incorrect. Fix = pass in gpu_id: int and make nvidia-smi --id use it

  2. Nvidia makes several oem, non-public, version of A100 such as PG506-230 which is part of the official and opensource driver supported device list. They are essentially A100 with different VRAM sizes. Remap this model so TVM can be matched to A100 correctly. There may be other gpus affected so added TODO to move this into a helper re-mapper method. Fix = manual remap.

TEST

  • PASSED on PG506-230 => remap to A100
  • PASSED on 4090 in a multi-gpu setup where id is > 0

@LeiWang1999

@Qubitium Qubitium marked this pull request as ready for review June 21, 2024 06:40
@Qubitium Qubitium changed the title Fix GPU detection in multigpu env and OEM A100 not matching TVM [FIX] GPU detection in multigpu env and OEM A100 not matching TVM Jun 21, 2024
@LeiWang1999 LeiWang1999 merged commit cca477e into microsoft:main Jun 21, 2024
1 check passed
@LeiWang1999
Copy link
Contributor

LGTM!

@Qubitium Qubitium deleted the fix-nvidia-smi-check branch June 21, 2024 10:22
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants