opencl: use flat mv q5_k when weight exceeds image1d_buffer_t limit - #26880
Merged
Conversation
github-actions
Bot
added
ggml
lhez
marked this pull request as ready for review
August 11, 2026 05:02
max-krasnyansky
approved these changes
Aug 11, 2026
lhez
added
the
merge ready
Contributor
Author
|
@ggml-org/maintainers can I please have another approval? |
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Aug 12, 2026
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * origin/master: (383 commits) cmake : introduce semantic versioning (ggml-org#26839) gguf : harden loader against malformed tensor dims and metadata types (ggml-org#25596) kleidiai: Add runtime feature detection mechanism for aarch64/kleidiai (ggml-org#26076) model : disallow integer dflash sliding_window_pattern (ggml-org#26900) sync : ggml cmake : add config version support (ggml/1582) server : support slot save/restore with media inputs (ggml-org#26640) ui: add read_media tool (ggml-org#25877) opencl: default FA c8 cluster width to 16 on X1E (ggml-org#26433) tests : update speculative params (ggml-org#26925) vulkan: add TQ2_0 (ternary) support (ggml-org#25850) wavtokenizer-dec : bound posnet/convnext block_count against n_layer_all (ggml-org#26892) convert : handle per_layer_config in Gemma4 (transformers 5.15) (ggml-org#26882) opencl: use flat mv q5_k when weight exceeds image1d_buffer_t limit (ggml-org#26880) chat : fix muse-glimmer detection of tool calls after EOM (ggml-org#26879) ci : add missing release check (ggml-org#26923) CUDA: only disable CUDA graphs when mul_mat_id actually needs a stream sync (ggml-org#26802) cuda : add warp-per-row wkv7 kernel for single-token decode (ggml-org#26111) spec : update speculative-simple (ggml-org#26904) chat : tighten bare function parsing for Qwen models (ggml-org#26793) ...
huaxel
pushed a commit
to huaxel/CachyLLama
that referenced
this pull request
Aug 12, 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
This PR uses flat q5_K mv for large q5_K weights.
The Adreno gemv_noshuffle kernels use image1d_buffer_t for weights. If weights matrix is too large and exceeds the max allowed size of image1d_buffer_t, image creation will fail and the application will crash. In such cases, flat mv kernels have to be used (we should do this check for all other quantizations in future PR).
Additional information
Requirements