llama-quant: add support for mmproj #16592
Merged
+19
−2
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
ggerganov
approved these changes
Oct 15, 2025
CISC
approved these changes
Oct 15, 2025
Co-authored-by: Georgi Gerganov <[email protected]>
CISC
reviewed
Oct 15, 2025
yael-works
pushed a commit
to yael-works/llama.cpp
that referenced
this pull request
Oct 15, 2025
* llama-quant: add support for mmproj * Update src/llama.cpp Co-authored-by: Georgi Gerganov <[email protected]> * check prefix instead * small fix --------- Co-authored-by: Georgi Gerganov <[email protected]>
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Oct 15, 2025
* origin/master: Add server-driven parameter defaults and syncing (ggml-org#16515) metal: optimise `GGML_OP_SUM` (ggml-org#16559) server : fix img token logs (ggml-org#16595) llama-quant: add support for mmproj (ggml-org#16592) CUDA: Changing the CUDA scheduling strategy to spin (ggml-org#16585) server : fix mtmd checkpoints (ggml-org#16591) metal : avoid using Metal's gpuAddress property (ggml-org#16576) vulkan: Add ACC_TYPE_VEC2 implementation (ggml-org#16203) CUDA + openCL: fix bug in accessing rms_norm->src while doing fusion (ggml-org#16577) vulkan: Support FA with K/V in F32 (ggml-org#16543) vulkan: Improve build time for MSVC (ggml-org#16545) CUDA: enable FA for FP32 KV cache (ggml-org#16546) CUDA: use fastdiv + ggml_cuda_mad for mmvf (ggml-org#16557) CUDA: add fp kernel for larger batch size MoE (ggml-org#16512) cuda : remove legacy copy-op pointer indirection code (ggml-org#16485) server : dynamic token limit for prompt cache (ggml-org#16560)
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 allows
llama-quantizeto work with mmproj. It should allow quantizing mmproj to Qx_K and Qx_0 variants (no imatrix), reducing memory usage on mobile deployments.Tested with https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct
To quantize the mmproj:
Then, use it as usual:
Ref discussion: #15453