Fix segfault in moe-expert-reduce test in support mode and coverage#16936
Merged
slaren merged 4 commits intoggml-org:masterfrom Nov 2, 2025
Merged
Fix segfault in moe-expert-reduce test in support mode and coverage#16936slaren merged 4 commits intoggml-org:masterfrom
slaren merged 4 commits intoggml-org:masterfrom
Conversation
Contributor
Author
|
@am17an Please review |
slaren
requested changes
Nov 2, 2025
Member
slaren
left a comment
There was a problem hiding this comment.
It would be better to filter out fusion cases in the supports test, but also initialize gf in eval_support.
Contributor
Author
|
Thanks @slaren, I incorporated your suggestions. Please let me know if this was the intended approach |
slaren
reviewed
Nov 2, 2025
sbera77
commented
Nov 2, 2025
slaren
reviewed
Nov 2, 2025
Contributor
Author
|
@slaren Thank you for your guidance and feedback. Please have a look
|
slaren
approved these changes
Nov 2, 2025
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Nov 3, 2025
* origin/master: (169 commits) opencl: support imrope (ggml-org#16914) fix: Viewing multiple PDF attachments (ggml-org#16974) model-conversion : pass config to from_pretrained (ggml-org#16963) server : add props.model_alias (ggml-org#16943) ggml: CUDA: add head size 72 for flash-attn (ggml-org#16962) mtmd: add --image-min/max-tokens (ggml-org#16921) mtmd: pad mask for qwen2.5vl (ggml-org#16954) ggml : LoongArch fixes (ggml-org#16958) sync: minja (glm 4.6 & minmax m2 templates) (ggml-org#16949) SYCL: optimized repeat_back kernel (3× fewer asm instructions, 2× faster)Feature/sycl repeat back opt (ggml-org#16869) feat(webui): improve LaTeX rendering with currency detection (ggml-org#16508) test-backend-ops : fix segfault in moe-expert-reduce test in support mode and coverage (ggml-org#16936) ci : disable failing riscv cross build (ggml-org#16952) model: add Janus Pro for image understanding (ggml-org#16906) clip : use FA (ggml-org#16837) server : support unified cache across slots (ggml-org#16736) common : move gpt-oss reasoning processing to init params (ggml-org#16937) docs: remove llama_sampler_accept reference in sampling sample usage (ggml-org#16920) CUDA: add FLOOR, CEIL, ROUND, TRUNC unary ops (ggml-org#16917) devops: fix failing s390x docker build (ggml-org#16918) ...
Anico2
added a commit
to Anico2/llama.cpp
that referenced
this pull request
Jan 15, 2026
…mode and coverage (ggml-org#16936) * tests: fix segfault in moe-expert-reduce test in support mode and --show-coverage * tests: init gf and filter out fusion tests for support mode * tests: filter out fusion cases before calling eval_support * tests: filter out fusion cases from show_test_coverage as well, fix lint
blime4
referenced
this pull request
in blime4/llama.cpp
Feb 5, 2026
…mode and coverage (#16936) * tests: fix segfault in moe-expert-reduce test in support mode and --show-coverage * tests: init gf and filter out fusion tests for support mode * tests: filter out fusion cases before calling eval_support * tests: filter out fusion cases from show_test_coverage as well, fix lint
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.
This PR fixes a segmentation fault that occurs while running the
test-backend-opstool insupportmode or with--show-coverageflag. This will also allowdocs/ops.mdto be updated for tracking #14909 as it needs the results fromsupportmode.Root Cause
Testing does not initialize
gf(ggml_cgraph), it callsbuild_graphmethod for each test case. Thetest_moe_expert_reducetest case callsggml_build_forward_expand(gf, ...)inside itsbuild_graphmethod butgfis anullptrin this flow which causes a seg fault.Solution
Wrap the
ggml_build_forward_expandcall in agfnull check.