[ET-VK][qlinear] Faster weight only quantized linear gemv kernel #12610
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Pull Request resolved: #12444 ## Changes * Introduce a new compute shader for int4 linear's gemv cases that performs much better than the existing shader. This shader is inspired from MNN's gemv_1x1_conv_buf.cl shader. With this compute kernel, transformer models' text generation can execute much faster than before. On Samsung Galaxy S24 for Llama 3.2 1B, generating 128 tokens: Before: ~25 tok/s After: ~49 tok/s ## Why this new shader is faster The biggest reason is due to vectorized loading of the uint4 weight buffer. This new shader loads the weight buffer as a buffer/image of `uvec4`, whereas the old shader loads the weight buffer as a buffer/image of `u8vec4`. Using the Adreno Offline Compiler, I found that in the former, only one load instruction was used to load from the weight tensor, whereas in the latter 16 load instructions were used to load from the weight tensor. It appears that the data loading was not being vectorized at the assembly level. This is potentially behaviour that can be approved in the SPIR-V shader compiler. An additional factor is better weight packing layout. The new prepacking routine results in better memory coalescing between threads in a work group. The final major factor is the use of tree based reduction to co-operatively reduce partial results into the final output. Previously, a single thread was responsible for the final reduction. ## Future Work * Introduce faster shader for int4 linear gemm cases * Update QCSNW to also use these updated shaders ghstack-source-id: 296864718 Differential Revision: [D78275584](https://our.internmc.facebook.com/intern/diff/D78275584/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12610
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit 4b42e35 with merge base 924bbf8 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
SS-JIA
approved these changes
Jul 18, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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 was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #12444 by @SS-JIA
^ Please use this as the source of truth for the PR details, comments, and reviews
ghstack PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/259/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/259/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/main
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/259/orig
@diff-train-skip-merge