tests: skip broken archs in test-llama-archs#21783
Open
stephencox-ict wants to merge 1 commit intoggml-org:masterfrom
Open
tests: skip broken archs in test-llama-archs#21783stephencox-ict wants to merge 1 commit intoggml-org:masterfrom
stephencox-ict wants to merge 1 commit intoggml-org:masterfrom
Conversation
Skip architectures that crash, hang, or produce wrong results in test-llama-archs save_models() and test_backends(). These were found while running the full test suite across backends. save_models() skips: - CLIP, GPTJ: no usable implementations - CHAMELEON: half-implemented - RWKV6/RWKV6QWEN2/RWKV7/ARWKV7: hang or crash - BERT variants, EUROBERT: vocab issues - PLM: tensor shape mismatch test_backends() skips (all of the above, plus): - WAVTOKENIZER_DEC: CUDA backend crash - LLAMA_EMBED, GEMMA_EMBEDDING, T5ENCODER: inconsistent results - DEEPSEEK2OCR: tensor shape mismatch Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
Hi @stephencox-ict, thanks for your contribution! Per our contribution guidelines, the automated PR checker found the following issue(s) that need your attention:
Please note that maintainers reserve the right to make final decisions on PRs. If you believe there is a mistake, please comment below. |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Skip architectures in
test-llama-archsthat crash, hang, or produce incorrect results. Found while running the full test suite across CPU and GPU backends during work on #21421 (Gemma 4 audio conformer).save_models()skips:CLIP,GPTJ- no usable implementationsCHAMELEON- half-implemented, to be removedRWKV6,RWKV6QWEN2,RWKV7,ARWKV7- hang or crashBERTvariants,EUROBERT- vocab issuesPLM- tensor shape mismatchtest_backends()skips (all of the above, plus):WAVTOKENIZER_DEC- CUDA backend crashLLAMA_EMBED,GEMMA_EMBEDDING,T5ENCODER- inconsistent resultsDEEPSEEK2OCR- tensor shape mismatchThese skips only affect models that already fail. No passing tests are affected.
Ref: #21421
Requirements