enroll mxtensor in vllm integration tests #3081
Merged
+49
−19
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
|
Stack from ghstack (oldest at bottom): |
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3081
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit f962851 with merge base a53a4db ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
This was referenced Sep 26, 2025
vkuzo
added a commit
that referenced
this pull request
Sep 26, 2025
Summary: 1. enrolls mxtensor in existing vllm slice and copy test, make it pass by moving to TorchAOBaseTensor's copy 2. add an additional test for vllm narrow, make that test pass by fixing an incorrect slice implementation. This may be useful for other tensor, they can opt-in in separate PRs. Test Plan: ``` pytest test/prototype/mx_formats/ -s -x ``` also, this PR enables running mxfp4 weight-only Qwen MoE models in vllm Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: e79dfc3 ghstack-comment-id: 3339065416 Pull Request resolved: #3081
vkuzo
added a commit
that referenced
this pull request
Sep 26, 2025
Summary: 1. enrolls mxtensor in existing vllm slice and copy test, make it pass by moving to TorchAOBaseTensor's copy 2. add an additional test for vllm narrow, make that test pass by fixing an incorrect slice implementation. This may be useful for other tensor, they can opt-in in separate PRs. Test Plan: ``` pytest test/prototype/mx_formats/ -s -x ``` also, this PR enables running mxfp4 weight-only Qwen MoE models in vllm Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: bd1c041 ghstack-comment-id: 3339065416 Pull Request resolved: #3081
vkuzo
added a commit
that referenced
this pull request
Sep 26, 2025
Summary: 1. enrolls mxtensor in existing vllm slice and copy test, make it pass by moving to TorchAOBaseTensor's copy 2. add an additional test for vllm narrow, make that test pass by fixing an incorrect slice implementation. This may be useful for other tensor, they can opt-in in separate PRs. Test Plan: ``` pytest test/prototype/mx_formats/ -s -x ``` also, this PR enables running mxfp4 weight-only Qwen MoE models in vllm Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 609a88e ghstack-comment-id: 3339065416 Pull Request resolved: #3081
vkuzo
added a commit
that referenced
this pull request
Sep 26, 2025
Summary: 1. enrolls mxtensor in existing vllm slice and copy test, make it pass by moving to TorchAOBaseTensor's copy 2. add an additional test for vllm narrow, make that test pass by fixing an incorrect slice implementation. This may be useful for other tensor, they can opt-in in separate PRs. Test Plan: ``` pytest test/prototype/mx_formats/ -s -x ``` also, this PR enables running mxfp4 weight-only Qwen MoE models in vllm Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 609a88e ghstack-comment-id: 3339065416 Pull Request resolved: #3081
vkuzo
added a commit
that referenced
this pull request
Sep 26, 2025
Summary: 1. enrolls mxtensor in existing vllm slice and copy test, make it pass by moving to TorchAOBaseTensor's copy 2. add an additional test for vllm narrow, make that test pass by fixing an incorrect slice implementation. This may be useful for other tensor, they can opt-in in separate PRs. Test Plan: ``` pytest test/prototype/mx_formats/ -s -x ``` also, this PR enables running mxfp4 weight-only Qwen MoE models in vllm Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 609a88e ghstack-comment-id: 3339065416 Pull Request resolved: #3081
vkuzo
added a commit
that referenced
this pull request
Sep 26, 2025
Summary: 1. enrolls mxtensor in existing vllm slice and copy test, make it pass by moving to TorchAOBaseTensor's copy 2. add an additional test for vllm narrow, make that test pass by fixing an incorrect slice implementation. This may be useful for other tensor, they can opt-in in separate PRs. Test Plan: ``` pytest test/prototype/mx_formats/ -s -x ``` also, this PR enables running mxfp4 weight-only Qwen MoE models in vllm Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 609a88e ghstack-comment-id: 3339065416 Pull Request resolved: #3081
vkuzo
added a commit
that referenced
this pull request
Sep 26, 2025
Summary: 1. enrolls mxtensor in existing vllm slice and copy test, make it pass by moving to TorchAOBaseTensor's copy 2. add an additional test for vllm narrow, make that test pass by fixing an incorrect slice implementation. This may be useful for other tensor, they can opt-in in separate PRs. Test Plan: ``` pytest test/prototype/mx_formats/ -s -x ``` also, this PR enables running mxfp4 weight-only Qwen MoE models in vllm Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 609a88e ghstack-comment-id: 3339065416 Pull Request resolved: #3081
jerryzh168
approved these changes
Sep 26, 2025
vkuzo
added a commit
that referenced
this pull request
Sep 27, 2025
Summary: 1. enrolls mxtensor in existing vllm slice and copy test, make it pass by moving to TorchAOBaseTensor's copy 2. add an additional test for vllm narrow, make that test pass by fixing an incorrect slice implementation. This may be useful for other tensor, they can opt-in in separate PRs. Test Plan: ``` pytest test/prototype/mx_formats/ -s -x ``` also, this PR enables running mxfp4 weight-only Qwen MoE models in vllm Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 609a88e ghstack-comment-id: 3339065416 Pull Request resolved: #3081
This was referenced Sep 27, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Summary:
by moving to TorchAOBaseTensor's copy
an incorrect slice implementation. This may be useful for other
tensor, they can opt-in in separate PRs.
Test Plan:
also, this PR enables running mxfp4 weight-only Qwen MoE models in vllm
Reviewers:
Subscribers:
Tasks:
Tags: