Support aoti_torch_cuda__weight_int4pack_mm #15089
Merged
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
Summary: When quantizing a model with 4w_hqq (huggingface/optimum-executorch#164), AOTI-generated code will call aoti_torch_cuda__weight_int4pack_mm as a fallback op. This PR borrows the CUDA implementation of _weight_int4pack_mm_cuda from libtorch, by replacing at::Tensor and relevant utility functions with ET equivalents. Using the Voxtral runner as an example, With the bfloat16 format, here is the generated ptd file size and latency. ``` aoti_cuda_blob.ptd: 9.0 GB Program load latency (ms): 0.054 Method load latency (ms): audio_encoder: 1492.989 token_embedding: 803.561 text_decoder: 6556.770 Run latency (ms): audio_encoder: 76.848 token_embedding: 6.479 text_decoder: 149.128 ``` With `--qlinear 4w_hqq --qlinear_encoder 4w_hqq`, the ptd file size is cut more than half, with slowdowns in the encoder and decoder parts. ``` aoti_cuda_blob.ptd: 3.7 GB Program load latency (ms): 0.051 Method load latency (ms): audio_encoder: 716.667 token_embedding: 633.476 text_decoder: 1840.760 Run latency (ms): audio_encoder: 329.274 token_embedding: 4.285 text_decoder: 335.590 ``` ghstack-source-id: 29b5b16 Pull Request resolved: #15030
pytorchbot
requested review from
kirklandsign and
larryliu0820
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15089
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 4 Unrelated FailuresAs of commit b571906 with merge base afd98fe ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following jobs failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
mergennachin
approved these changes
Oct 14, 2025
|
@pytorchbot label "release notes: none" |
pytorch-bot
bot
added
the
release notes: none
|
@mergennachin , do you know why this PR was auto-created? I thought #15030 is already merged? |
|
@desertfire - oh yeah, your other PR merged not in main but to your private branch. this is mainly userful for ghstack. we have a slightly different flow than core. you need to land this PR |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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: #15030 by @desertfire
^ 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/desertfire/1/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/desertfire/1/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/main
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/desertfire/1/orig
Differential Revision: D84395275
@diff-train-skip-merge