Skip to content

Pull requests: quic/efficient-transformers

New pull request New
37 Open 904 Closed
37 Open 904 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Optimize attention blocking nested loops
#957 opened Apr 30, 2026 by anujgupt-github Contributor Loading…
@anujgupt-github
Layer wise changes for kimi model
#954 opened Apr 29, 2026 by abhishek-singh591 Contributor Loading…
[Nightly CI]: Creating separate Pipeline for Nightly Jobs
#953 opened Apr 29, 2026 by abukhoy Contributor Loading…
fix: improve weight offloading to handle plain tensor attrs and use to_empty()
#952 opened Apr 28, 2026 by quic-rishinr Contributor Loading…
Add SplitTensorsTransform to QEFFAutoModel to prevent >2GB protobuf export issue
#950 opened Apr 28, 2026 by quic-rishinr Contributor Loading…
1
MLA Int4 changes
#949 opened Apr 28, 2026 by quic-mamta Contributor Loading…
@quic-mamta
Gemma4 alignment
#948 opened Apr 28, 2026 by tchawada Contributor • Draft
1
First Block Caching Infra for diffusers Diffusers Use for PR related to diffusers in efficient-transformers.
#941 opened Apr 24, 2026 by quic-amitraj Contributor Loading…
@quic-amitraj
feat(moe): NSP-blocked expert dispatch for Qwen3MOE and GPT-OSS prefill enhancement New feature or request
#935 opened Apr 21, 2026 by vbaddi Contributor Loading…
@vbaddi @quic-mamta
3
updated blocking in diffusers with cross attention check instead of SL
#932 opened Apr 21, 2026 by tv-karthikeya Contributor Loading…
Added MDP generation to QEff Compile
#930 opened Apr 21, 2026 by quic-mohmeh Loading…
2
CB Bug fix for Qwen3VL Dense and basic cleaning of example script and Model File
#926 opened Apr 20, 2026 by qcdipankar Contributor Loading…
1
Enabled Qwen3-VL embedding model
#923 opened Apr 20, 2026 by quic-amitraj Contributor Loading…
@quic-amitraj
2
[Qwen3_Omni]_Onboarding
#922 opened Apr 20, 2026 by mohiso22 Contributor • Draft
Enabling support of rerankers models 2B and 8B of qwen3vl
#921 opened Apr 18, 2026 by quic-amitraj Contributor Loading…
@quic-amitraj
Removed redundancies from QEFFHybridCache and QEFFHybridChunkedCache
#914 opened Apr 13, 2026 by quic-mamta Contributor • Draft
@quic-mamta
1
revert(export): Revert proxy-only ONNX transform gating and restore default export behavior 1.21.0
#912 opened Apr 10, 2026 by vbaddi Contributor Loading…
@abhishek-singh591
[QEff. Finetuning] Adding TP+DDP support in HF Trainer stack
#907 opened Apr 6, 2026 by smedhe Contributor • Draft
2
feat: Enable benchmark-mode module inventory/export across all CausalLM architectures enhancement New feature or request
#906 opened Apr 3, 2026 by vbaddi Contributor Loading…
4
feat(Llama GQA): optional shared-KV matmul rewrite for attention. WIP: (env-gated)
#905 opened Apr 3, 2026 by vbaddi Contributor • Draft
qwen3_5_linear_attn
#901 opened Apr 1, 2026 by mohiso22 Contributor • Draft
Added performance analysis as a feature with AutoModelForCausalLM
#888 opened Mar 25, 2026 by ochougul Contributor • Draft
@ochougul
Merge ft_experimental_v1 branch to main fine-tuning ready for review
#887 opened Mar 25, 2026 by quic-akuruvil Contributor Loading…
@quic-akuruvil @quic-swatia
@tchawada @smedhe
rebase(transformers): align modeling wrappers, cache_utils and other changes to v5.3.0 and restore PyTorch/ORT parity enhancement New feature or request
#876 opened Mar 21, 2026 by vbaddi Contributor • Draft
2 tasks
@vbaddi @asmigosw
1
Undo deepstack_features based changes for Qwen3VL and Qwen3VL_MOE models
#869 opened Mar 18, 2026 by quic-dhirajku Contributor • Draft
ProTip! What’s not been updated in a month: updated:<2026-03-30.