[CUTLASS] Add blockwise scale gemm/bmm kernels #17789
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR introduces blockwise scale matmul and batch matmul CUTLASS kernels, adapted from SGLang (http://github.com/sgl-project/sglang), vLLM (https://github.com/vllm-project/vllm) and
https://github.com/soundOfDestiny/cutlass.
We add unit tests for gemm and bmm. This PR also restores some cutlass gemm tests that were removed before during Relay phasing out.