Fix garbled output with REPACK at high thread counts#16956
Merged
max-krasnyansky merged 3 commits intoggml-org:masterfrom Nov 4, 2025
Merged
Fix garbled output with REPACK at high thread counts#16956max-krasnyansky merged 3 commits intoggml-org:masterfrom
max-krasnyansky merged 3 commits intoggml-org:masterfrom
Conversation
Fixed a race condition in the REPACK matrix multiplication code that caused garbled output when using 26+ threads (model-dependent threshold). The issue occurred because with high thread counts, the code forced chunk count to equal thread count, creating many small chunks. After aligning these chunks to NB_COLS boundaries, adjacent chunks could overlap, causing data corruption and race conditions. The fix enforces minimum chunk sizes based on NB_COLS and caps maximum chunk count to prevent creating too many tiny chunks, ensuring proper alignment without overlaps.
Contributor
Author
|
I can't reproduce #16960 with this fix anymore. |
ggerganov
approved these changes
Nov 3, 2025
Member
ggerganov
left a comment
There was a problem hiding this comment.
Think this is OK, but would be nice if @max-krasnyansky can take a look as well.
ggerganov
reviewed
Nov 3, 2025
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Collaborator
|
Hmm. The change looks good but I'm seeing a significant regression in token rates from my earlier testing. |
Collaborator
False alarm. Merging ... |
max-krasnyansky
approved these changes
Nov 4, 2025
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Nov 5, 2025
* origin/master: (21 commits) vulkan: Fix GGML_VULKAN_CHECK_RESULTS to better handle fusion (ggml-org#16919) examples(gguf): GGUF example outputs (ggml-org#17025) mtmd: allow QwenVL to process larger image by default (ggml-org#17020) server : do not default to multiple slots with speculative decoding (ggml-org#17017) mtmd: improve struct initialization (ggml-org#16981) docs: Clarify the endpoint that webui uses (ggml-org#17001) model : add openPangu-Embedded (ggml-org#16941) ggml webgpu: minor set rows optimization (ggml-org#16810) sync : ggml ggml : fix conv2d_dw SVE path (ggml/1380) CUDA: update ops.md (ggml-org#17005) opencl: update doc (ggml-org#17011) refactor: replace sprintf with snprintf for safer string handling in dump functions (ggml-org#16913) vulkan: remove the need for the dryrun (ggml-org#16826) server : do context shift only while generating (ggml-org#17000) readme : update hot topics (ggml-org#17002) ggml-cpu : bicubic interpolation (ggml-org#16891) ci : apply model label to models (ggml-org#16994) chore : fix models indent after refactor (ggml-org#16992) Fix garbled output with REPACK at high thread counts (ggml-org#16956) ...
|
Thank you! This fixed Unsloth's Qwen3-VL-30B-A3B-Instruct-1M GGUF quants. Also, this had made other quants more coherent, including Wayfarer-2. Great work guys! I think this will positively affect more GGUF quants than we can rightly quantify. For reference: I tested with the METAL backend on an M1 MacBook Pro 16GB (Unified Memory). |
Anico2
added a commit
to Anico2/llama.cpp
that referenced
this pull request
Jan 15, 2026
* Fix garbled output with REPACK at high thread counts Fixed a race condition in the REPACK matrix multiplication code that caused garbled output when using 26+ threads (model-dependent threshold). The issue occurred because with high thread counts, the code forced chunk count to equal thread count, creating many small chunks. After aligning these chunks to NB_COLS boundaries, adjacent chunks could overlap, causing data corruption and race conditions. The fix enforces minimum chunk sizes based on NB_COLS and caps maximum chunk count to prevent creating too many tiny chunks, ensuring proper alignment without overlaps. * Update ggml/src/ggml-cpu/repack.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml/src/ggml-cpu/repack.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
blime4
referenced
this pull request
in blime4/llama.cpp
Feb 5, 2026
* Fix garbled output with REPACK at high thread counts Fixed a race condition in the REPACK matrix multiplication code that caused garbled output when using 26+ threads (model-dependent threshold). The issue occurred because with high thread counts, the code forced chunk count to equal thread count, creating many small chunks. After aligning these chunks to NB_COLS boundaries, adjacent chunks could overlap, causing data corruption and race conditions. The fix enforces minimum chunk sizes based on NB_COLS and caps maximum chunk count to prevent creating too many tiny chunks, ensuring proper alignment without overlaps. * Update ggml/src/ggml-cpu/repack.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml/src/ggml-cpu/repack.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
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
5 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.
Fixed a race condition in the REPACK matrix multiplication code that caused garbled output when using 26+ threads (model-dependent threshold). The issue occurred because with high thread counts, the code forced chunk count to equal thread count, creating many small chunks. After aligning these chunks to NB_COLS boundaries, adjacent chunks could overlap, causing data corruption and race conditions. The fix enforces minimum chunk sizes based on NB_COLS and caps maximum chunk count to prevent creating too many tiny chunks, ensuring proper alignment without overlaps.