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

Update ROCM libs and improvements #2579

Merged
merged 29 commits into from
Sep 30, 2024
Merged

Update ROCM libs and improvements #2579

merged 29 commits into from
Sep 30, 2024

Conversation

mht-sharma
Copy link
Collaborator

What does this PR do?

This PR introduces various library updates to address breaking changes, including optimisations for ROCm and custom kernels for low-batch-size GEMM and Paged attention. Key improvements are as follows:

  • Update CK flash attention to use CK tile
  • Update VLLM to latest rocm/vllm commit.
  • Update torch
  • Fix tunable op issue with TP8
  • BF16 inference fix
  • Custom Paged attention
  • Documentation

@mht-sharma mht-sharma requested a review from danieldk September 27, 2024 13:11
@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@mht-sharma mht-sharma changed the title [Tmp] Update ROCM libs and improvements Update ROCM libs and improvements Sep 27, 2024
@danieldk danieldk merged commit f9e561e into main Sep 30, 2024
19 of 20 checks passed
@danieldk danieldk deleted the rocm_6.2_updates branch September 30, 2024 08:54
yuanwu2017 pushed a commit to yuanwu2017/tgi-gaudi that referenced this pull request Oct 27, 2024
* style

* update torch

* ix issues

* fix clone

* revert mkl

* added custom PA

* style

* fix style

* style

* hide env vart

* fix mixtral model

* add skinny kernel and merge fixes

* fixed style

* fix issue for sliding window models

* addressed review comments

* fix import

* improved error messag

* updated default value

* remove import

* fix imports after rebase

* float16 dep

* improve dockerfile

* cleaned dockerfile
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