mtmd: fix gemma 4 projector pre_norm#23822
Merged
Merged
Conversation
CISC
approved these changes
May 28, 2026
Contributor
Author
|
asking for 2nd approval @ggml-org/maintainers 🙏 |
ServeurpersoCom
approved these changes
May 28, 2026
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
May 28, 2026
* origin/master: (32 commits) hexagon: basic/generic op fusion support and RMS_NORM+MUL fusion (ggml-org#23835) mtmd-debug: add color and rainbow mode (ggml-org#23829) mtmd: fix gemma 4 projector pre_norm (ggml-org#23822) opencl: move backend info printing into its own function (ggml-org#23702) ci : run ui publish on ubuntu-slim (ggml-org#23818) ui: fix audio and video modality detection (ggml-org#23756) ci : releases use Github-hosted builds for the UI (ggml-org#23823) app : improve help output (ggml-org#23805) mtmd: n_head_kv defaults to n_head (ggml-org#23782) mtmd: fix gemma 4 audio rms norm eps (ggml-org#23815) ci : change Vulkan builds to Release to reduce ccache (ggml-org#23820) arg: Add LLAMA_ARG_API_KEY_FILE environment variable for --api-key-file (ggml-org#23167) test-llama-archs: fix table format [no release] (ggml-org#23810) ggml: auto apply iGPU flag CUDA/HIP if integrated device (ggml-org#23007) mmvq Optim: add MMVQ_PARAMETERS_TURING(mmvq_parameter_table_id) for … (ggml-org#23729) CUDA: route batch>=4 quantized matmul to MMQ on AMD MFMA hardware (ggml-org#23227) server: minor tweaks to use more cpp features (ggml-org#23785) hexagon: minor refresh for HMX FA and MM (ggml-org#23796) vulkan: fast path for walsh-hadamard transform (ggml-org#23687) chat : add Granite 4.1 chat template (ggml-org#23518) ...
fewtarius
pushed a commit
to fewtarius/llama.cpp
that referenced
this pull request
May 30, 2026
turbo-tan
pushed a commit
to turbo-tan/llama.cpp-tq3
that referenced
this pull request
Jun 2, 2026
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
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.
Overview
The early pre-release version of gemma 4 uses post norm for multimodal projector, but it was later swapped to pre-norm and I did not notice about that.
This should fix some vision-related problems with gemma 4.
Ref python code: https://github.com/huggingface/transformers/blob/1656d90b774d94c30af24113e60e926fc2f39072/src/transformers/models/gemma4/modeling_gemma4.py#L2068-L2092
Test:
Requirements