Fix mamba caches#40196
Closed
manueldeprada wants to merge 18 commits intohuggingface:mainfrom
Closed
Conversation
… option (huggingface#39953) * Fix MXFP4 quantizer validation to enable CPU dequantization Move dequantize check before CUDA availability check to allow CPU inference when quantization_config.dequantize is True. This enables users to run MXFP4 models on CPU by automatically converting them to BF16 format. * Add tests for MXFP4 quantizer CPU dequantization validation * fix: format mxfp4 test file with ruff
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
* remove dep * style * rm import * fix * style * simplify * style
* Fix missing video inputs for PerceptionLM. * Minor fix for vanilla input image (only C,H,W, no tiles dim). * Revert "Minor fix for vanilla input image (only C,H,W, no tiles dim)." This reverts commit 181d87b.
* fix fuyu Signed-off-by: Isotr0py <2037008807@qq.com> * oops Signed-off-by: Isotr0py <2037008807@qq.com> * run test on GPU Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn> * clean unused Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn> * revert Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn> * add fuyu multimodal test Signed-off-by: Isotr0py <2037008807@qq.com> * fix Signed-off-by: Isotr0py <2037008807@qq.com> --------- Signed-off-by: Isotr0py <2037008807@qq.com> Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
…mask (huggingface#39991) (huggingface#40024) * Fix missing None default values for Gemma3n model in get_placeholder_mask (huggingface#39991) * Switched definition of optional from| None to Optiona[] (Issue huggingface#39991) --------- Co-authored-by: Laurenz Ruzicka <Laurenz.Ruzicka@ait.ac.at>
…ce#39986) * fix: resolve triton version check compatibility on windows * style: remove trailing space * fix: fix typo --------- Co-authored-by: Mohamed Mekkouri <93391238+MekkCyber@users.noreply.github.com>
* fix * update integration tests * fmt * add regression test
* default to dq if cpu * an other check * style * revert some changes
…gface#39975) * [bugfix] ensure correct tensor device in Idefics2, Idefics3, and SmolVLM models * to cuda
manueldeprada
added
the
for patch
manueldeprada
force-pushed
the
fix-mamba-caches
branch
from
df09a44 to
56a7903
Compare
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
15 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 takes as base v4.55.2 and adds the fix for mamba-style caches from #39797
Tested with vllm-main.