enable select for NVFP4Tensor #3117
Open
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): |
vkuzo
added a commit
that referenced
this pull request
Oct 2, 2025
Summary: This is useful for vLLM 2d -> 3d MoE weight surgery Test Plan: unit tests: ``` pytest test/prototype/mx_formats/ -s ``` Also, after this PR we can run a Qwen 1.5 MoE model quantized with nvfp4 in vLLM, with vllm-project/vllm#25480 Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: db79143 ghstack-comment-id: 3361104836 Pull-Request: #3117
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3117
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit b245367 with merge base 8955739 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
vkuzo
added
the
topic: improvement
vkuzo
added a commit
that referenced
this pull request
Oct 2, 2025
Summary: This is useful for vLLM 2d -> 3d MoE weight surgery Test Plan: unit tests: ``` pytest test/prototype/mx_formats/ -s ``` Also, after this PR we can run a Qwen 1.5 MoE model quantized with nvfp4 in vLLM, with vllm-project/vllm#25480 Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 6d7d385 ghstack-comment-id: 3361104836 Pull-Request: #3117
jcaip
reviewed
Oct 2, 2025
| new = old.__class__( | ||
| old.qdata[index], | ||
| old._scale_e4m3[index], | ||
| old._block_size, |
There was a problem hiding this comment.
should a dim get knocked off block size after you select?
There was a problem hiding this comment.
currently block_size is an integer for this tensor, 16 for NVFP4. If we change it to a multidimensional block, we'd have to update this code.
jcaip
approved these changes
Oct 2, 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.
Summary:
This is useful for vLLM 2d -> 3d MoE weight surgery
Test Plan:
unit tests:
Also, after this PR we can run a Qwen 1.5 MoE model quantized with nvfp4
in vLLM, with vllm-project/vllm#25480
Reviewers:
Subscribers:
Tasks:
Tags: