Skip to content

Conversation

@wenhuach21
Copy link
Contributor

@wenhuach21 wenhuach21 commented May 29, 2024

w2g32 accuracy verified, ok
mixed bits verified, ok
issue: triton kernel issue for low cuda version

@wenhuach21
Copy link
Contributor Author

Credit goes to @Qubitium (AutoGPTQ/AutoGPTQ#640) and the GPTQ community.

@wenhuach21 wenhuach21 changed the title Fix asym by following autogptq's pr [WIP]Fix asym by following autogptq's pr May 29, 2024
@wenhuach21 wenhuach21 changed the title [WIP]Fix asym by following autogptq's pr [WIP]Fix asym kernel issue by following autogptq's pr May 29, 2024
@wenhuach21 wenhuach21 changed the title [WIP]Fix asym kernel issue by following autogptq's pr Fix asym kernel issue by following autogptq's pr May 31, 2024
@wenhuach21 wenhuach21 merged commit 794cd90 into main Jun 3, 2024
@wenhuach21 wenhuach21 deleted the fix_asym branch June 3, 2024 05:04
attafosu pushed a commit to attafosu/auto-round that referenced this pull request Jul 23, 2024
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
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.

3 participants