ggml-cpu : disable tiled matmul on AIX to fix page boundary segfault#22293
Merged
ggerganov merged 4 commits intoggml-org:masterfrom Apr 29, 2026
Merged
ggml-cpu : disable tiled matmul on AIX to fix page boundary segfault#22293ggerganov merged 4 commits intoggml-org:masterfrom
ggerganov merged 4 commits intoggml-org:masterfrom
Conversation
vec_xst operations in the tiled path crash on AIX when writing near 4KB page boundaries due to strict memory protection. Fall back to mnpack implementation on AIX for stable execution. Signed-off-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com>
Contributor
Author
|
@taronaeo Request to review this patch . Thanks in advance. |
Contributor
Author
|
@ggerganov Request to review this patch. Thanks in advance |
Co-authored-by: Aaron Teo <taronaeo@gmail.com>
github-actions
Bot
added
the
ggml
Contributor
Author
|
@taronaeo |
Member
|
Noted on the CI failures. All seem unrelated to this PR. |
taronaeo
approved these changes
Apr 24, 2026
CISC
approved these changes
Apr 24, 2026
Contributor
Author
Contributor
Author
|
@ggerganov can you please help review this patch ? |
tekintian
added a commit
to tekintian/llama.cpp
that referenced
this pull request
May 1, 2026
* 'master' of github.com:tekintian/llama.cpp: (659 commits) ggml-webgpu: Improve performance of mat-vec and mat-mat for MUL_MAT_ID (ggml-org#22464) Update llama-mmap to use ftello/fseeko (ggml-org#22497) common : check for null getpwuid in hf-cache (ggml-org#22550) vulkan: add get/set tensor 2d functions (ggml-org#22514) spec: fix argument typo (ggml-org#22552) ci : bump ty to 0.0.33 (ggml-org#22535) vendor : update cpp-httplib to 0.43.2 (ggml-org#22548) CUDA: fix tile FA kernel on Pascal (ggml-org#22541) scripts : add wc2wt.sh - create worktree from current HEAD (ggml-org#22513) add fast matmul iquants (ggml-org#22504) spec : fix draft model checkpoints (ggml-org#22521) spec : fix vocab compat checks in spec example (ggml-org#22426) common : do not pass prompt tokens to reasoning budget sampler (ggml-org#22488) hexagon: make vmem and buffer-size configurable (ggml-org#22487) CUDA: fuse SSM_CONV + ADD(bias) + SILU (ggml-org#22478) spec : disacard last drafted token with low prob (ggml-org#22506) sync : ggml ggml : bump version to 0.10.1 (ggml/1469) webui: fix slow mic stop and WAV encode (ggml-org#22480) ggml-cpu : disable tiled matmul on AIX to fix page boundary segfault (ggml-org#22293) ... # Conflicts: # .gitignore
rsenthilkumar6
pushed a commit
to rsenthilkumar6/llama.cpp
that referenced
this pull request
May 1, 2026
…gml-org#22293) * ggml-cpu : disable tiled matmul on AIX to fix page boundary segfault vec_xst operations in the tiled path crash on AIX when writing near 4KB page boundaries due to strict memory protection. Fall back to mnpack implementation on AIX for stable execution. Signed-off-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com> * Update ggml/src/ggml-cpu/llamafile/sgemm.cpp Co-authored-by: Aaron Teo <taronaeo@gmail.com> * Update sgemm.cpp * Update sgemm.cpp --------- Signed-off-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com> Co-authored-by: Aaron Teo <taronaeo@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
4 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.
vec_xst operations in the tiled path crash on AIX when writing near 4KB page boundaries due to strict memory protection. Fall back to mnpack implementation on AIX for stable execution.
Overview
This patch fixes segmentation faults in q4_0 model inference on AIX PowerPC systems by disabling the tiled matrix multiplication path in llamafile's sgemm implementation.
vec_xstoperations crash on AIX when writing near 4KB page boundaries due to strict memory protection. Thevec_xstinstruction cannot write across page boundaries on AIX, and when the buffer offset lands at addresses like0x1100ed000(exactly at a page boundary), the write operation attempts to access unmapped memory, triggering a segfault.This issue does not occur on Linux because Linux has more lenient memory management and may have adjacent pages already mapped. On AIX, page boundaries are strictly enforced.
Additional information
Requirements