Enable RMSNorm substitution for Transformers backend
#26353
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
This change should enable quant fusions which depend on the `RMSNorm` op being present Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
I've reviewed your changes to enable RMSNorm substitution. The approach to differentiate between RMSNorm and GemmaRMSNorm is clever, but I've identified a critical issue with handling weightless norms and a potential robustness improvement. Please see my detailed comments below.
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Isotr0py
reviewed
Oct 7, 2025
Comment on lines
+214
to
+215
| if weight_test is not None and torch.all(weight_test == 0): | ||
| return GemmaRMSNorm(**kwargs) |
There was a problem hiding this comment.
Can we simply check the existence of _norm function for GemmaRMSNorm?
https://github.com/huggingface/transformers/blob/50090c3fc82e1e0a06b4da366ea2fb6055d529e9/src/transformers/models/gemma3n/modeling_gemma3n.py#L123-L124
There was a problem hiding this comment.
That would work for Gemma models as they are currently implemented in Transformers. However:
- Custom models may not use this pattern
_normis a private method and so may change under us- A counter-example would be Moshi, which implements
_normbut doesx * winstead ofx * (1 + w)
github-actions
bot
added
the
ready
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
github-project-automation
bot
moved this from In Progress
to Done
in Transformers backend
845473182
pushed a commit
to dsxsteven/vllm_splitPR
that referenced
this pull request
Oct 10, 2025
…to loader * 'loader' of https://github.com/dsxsteven/vllm_splitPR: (778 commits) [torchao] Add support for ModuleFqnToConfig using regex (vllm-project#26001) Add: Support for multiple hidden layers in Eagle3 (vllm-project#26164) Enable `RMSNorm` substitution for Transformers backend (vllm-project#26353) [Model] Gemma3: Fix GGUF loading and quantization (vllm-project#26189) Bump Flashinfer to v0.4.0 (vllm-project#26326) Update Dockerfile and install runai-model-streamer[gcs] package (vllm-project#26464) [Core] Relax the LoRA max rank (vllm-project#26461) [CI/Build] Fix model nightly tests (vllm-project#26466) [Hybrid]: Decouple Kernel Block Size from KV Page Size (vllm-project#24486) [Core][KVConnector] Propagate all tokens on resumed preemptions (vllm-project#24926) [MM][Doc] Add documentation for configurable mm profiling (vllm-project#26200) [Hardware][AMD] Enable FlexAttention backend on ROCm (vllm-project#26439) [Bugfix] Incorrect another MM data format in vllm bench throughput (vllm-project#26462) [Bugfix] Catch and log invalid token ids in detokenizer #2 (vllm-project#26445) [Minor] Change warning->warning_once in preprocess (vllm-project#26455) [Bugfix] Set the minimum python version for gpt-oss (vllm-project#26392) [Misc] Redact ray runtime env before logging (vllm-project#26302) Separate MLAAttention class from Attention (vllm-project#25103) [Attention] Register FLASHMLA_SPARSE (vllm-project#26441) [Kernels] Modular kernel refactor (vllm-project#24812) ...
xuebwang-amd
pushed a commit
to xuebwang-amd/vllm
that referenced
this pull request
Oct 10, 2025
…26353) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: xuebwang-amd <xuebwang@amd.com>
Dhruvilbhatt
pushed a commit
to Dhruvilbhatt/vllm
that referenced
this pull request
Oct 14, 2025
…26353) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Dhruvil Bhatt <bhattdbh@amazon.com>
lywa1998
pushed a commit
to lywa1998/vllm
that referenced
this pull request
Oct 20, 2025
…26353) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
alhridoy
pushed a commit
to alhridoy/vllm
that referenced
this pull request
Oct 24, 2025
…26353) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
xuebwang-amd
pushed a commit
to xuebwang-amd/vllm
that referenced
this pull request
Oct 24, 2025
…26353) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: xuebwang-amd <xuebwang@amd.com>
0xrushi
pushed a commit
to 0xrushi/vllm
that referenced
this pull request
Oct 26, 2025
…26353) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: 0xrushi <6279035+0xrushi@users.noreply.github.com>
0xrushi
pushed a commit
to 0xrushi/vllm
that referenced
this pull request
Oct 26, 2025
…26353) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: 0xrushi <6279035+0xrushi@users.noreply.github.com>
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.
This change should enable quant fusions which depend on the
RMSNormop being present