Skip to content

Pull requests: quic/efficient-transformers

New pull request New
31 Open 570 Closed
31 Open 570 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

Adding Compute-Context-Length (CCL)
#612 opened Nov 7, 2025 by quic-rishinr Loading…
Continuous Batching for VLMs
#610 opened Nov 5, 2025 by asmigosw Loading…
removed platform sdk dependency
#609 opened Nov 5, 2025 by smedhe Loading…
Prefill+decode gpt oss 1.21.0 enhancement New feature or request
#608 opened Nov 5, 2025 by ochougul Loading…
@ochougul
1
[Exp]: Python 3.12 upgrade
#607 opened Nov 5, 2025 by abukhoy Loading…
Diffusers support
#604 opened Nov 4, 2025 by quic-amitraj • Draft
Dynamo-enabled ONNX Export
#602 opened Nov 3, 2025 by smedhe • Draft
@smedhe
Onnx Subfunction
#600 opened Oct 29, 2025 by abhishek-singh591 • Draft
Extend on-device sampling support for dual QPC VLMs
#597 opened Oct 24, 2025 by quic-xiyushi Loading…
1
[Test]: Models test configs in a single Config file
#596 opened Oct 22, 2025 by abukhoy Loading…
4
Modified qwen_2.5 modelling file to allow replicate_kv_script to work for custom num_kv_heads.
#595 opened Oct 18, 2025 by quic-dhirajku Loading…
[WIP]: Add early support for KV replication in VLMs
#594 opened Oct 18, 2025 by vbaddi Loading…
1
Wan 2.2 5 b
#593 opened Oct 17, 2025 by tv-karthikeya • Draft
Qwen2.5_vl multi frame inference
#591 opened Oct 17, 2025 by mohiso22 • Draft
2
Onboarding Qwen3VlMoe
#590 opened Oct 16, 2025 by qcdipankar • Draft
@qcdipankar
[Upgradation]: onnx opset version updated from 13 to 17
#587 opened Oct 14, 2025 by abukhoy Loading…
1
Add support of qwen_image
#585 opened Oct 13, 2025 by quic-amitraj • Draft
removed redundancies from QEFFHybridCache
#582 opened Oct 2, 2025 by ochougul Loading…
1
Onboarding OmniSVG
#578 opened Sep 27, 2025 by qcdipankar • Draft
@qcdipankar
Adding Compute-Context-Length (CCL)
#576 opened Sep 26, 2025 by vjanfaza Loading…
Example walk through on how to onboard a Causal LM on Qefficient Transformers.
#574 opened Sep 24, 2025 by quic-dhirajku Loading…
Logger Module For Efficient Transformers 1.21.0 wip Work in progress
#555 opened Sep 10, 2025 by quic-hemagnih • Draft
1
Embedding Model fix wip Work in progress
#548 opened Aug 28, 2025 by quic-amitraj • Draft
Added Multiframe Inference for llama4+internvl
#547 opened Aug 27, 2025 by aditjadh Loading…
Added memory optimization for onnx transforms
#538 opened Aug 12, 2025 by quic-rishinr Loading…
5
ProTip! What’s not been updated in a month: updated:<2025-10-07.