Skip to content

Pull requests: quic/efficient-transformers

New pull request New
50 Open 1,151 Closed
50 Open 1,151 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

Enable weightfree for causallm1
#1220 opened Jul 27, 2026 by amarquic Loading…
feat(ci): add performance regression tracking stage
#1218 opened Jul 27, 2026 by quic-amitraj Contributor Loading…
Moe gemma4 changes
#1217 opened Jul 27, 2026 by tchawada Contributor Loading…
2
Adding the tmp CI changes
#1216 opened Jul 25, 2026 by quic-rishinr Contributor Loading…
feat: Replace num_replicate_kv_heads with boolean replicate_kv_heads flag
#1212 opened Jul 24, 2026 by quic-dhirajku Contributor Loading…
2
Adding PagedAttention support for CausalLM models
#1209 opened Jul 23, 2026 by vaibverm Contributor Loading…
51
Adding mdp fix for PP + Blocking + Subfunction
#1203 opened Jul 22, 2026 by mohiso22 Contributor • Draft
1
Adding support for Flux2 klein
#1201 opened Jul 22, 2026 by quic-swatia Contributor Loading…
1
[release/v1.22.0]: updating docs for release/v1.22.0
#1196 opened Jul 21, 2026 by abukhoy Contributor Loading…
8
Introducing OptimizedMoeTransform
#1190 opened Jul 17, 2026 by ochougul Contributor Loading…
5
Add CCL support to Gemma4, Qwen3.5 (moe), and qwn3_vl models
#1188 opened Jul 17, 2026 by vjanfaza Contributor Loading…
4
Qwen3.6_Tiling
#1185 opened Jul 15, 2026 by mohiso22 Contributor Loading…
4
QEff library utility to capture environment/runtime/library metadata right after loading a model before any transforms are applied.
#1183 opened Jul 15, 2026 by quic-dhirajku Contributor Loading…
Move qeff-bug-fix agent into skills_studio/agents
#1182 opened Jul 14, 2026 by quic-rishinr Contributor Loading…
3 tasks done
1
feat(weight-free): weight-free ONNX export for causal LMs (dynamo path) 1.23 Release 1.23 Features enhancement New feature or request qeff.weightfree WeightFree Onnx Export based on Dyanmo and Meta state
#1181 opened Jul 13, 2026 by amarquic Loading…
3 tasks
@quic-amitraj @amarquic
13
[Causal-LM Test]: Adding causal lm test cases for diff configs
#1180 opened Jul 13, 2026 by abukhoy Contributor Loading…
13
fix: eliminate non-constant Slice ends in sliding-window CB subfunction
#1179 opened Jul 13, 2026 by quic-amitraj Contributor Loading…
4 tasks done
1
Feature/add glm ocr
#1177 opened Jul 12, 2026 by shagsood • Draft
Custom dtype - bf16/fp16 support
#1175 opened Jul 11, 2026 by asmigosw Contributor • Draft
test-dynamo(0711): add dynamo causal-lm test infra + fix gemma3 and qwen3_moe subfunction export 1.23 Release 1.23 Features onnx.dynamo wip Work in progress
#1174 opened Jul 11, 2026 by vbaddi Contributor • Draft
@vbaddi @quic-amitraj @smedhe
Add reported reproducer config test suite enhancement New feature or request
#1173 opened Jul 10, 2026 by anujgupt-github Contributor Loading…
@anujgupt-github
3
[nightly] Fix garbage output in VLM nightly tests
#1172 opened Jul 10, 2026 by quic-vishali Contributor • Draft
3
Updating blocking dummy tests qeff.blocking
#1171 opened Jul 10, 2026 by kdulla Contributor • Draft
@kdulla
fix: eliminate non-constant Slice ends in Gemma4 sliding-window CB subfunction 1.22 Release 1.22 candidate bugfix
#1170 opened Jul 9, 2026 by quic-amitraj Contributor Loading…
3 tasks done
@quic-amitraj
1
Gpt_oss prefill: avoid packed expert-axis slicing in chunked MoE to restore MXFP6 constant compression
#1165 opened Jul 8, 2026 by abhishek-singh591 Contributor Loading…
7
ProTip! Exclude everything labeled bug with -label:bug.