Skip to content

Pull requests: quic/efficient-transformers

New pull request New
56 Open 1,163 Closed
56 Open 1,163 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

Updating MOE in Mixtral
#1238 opened Aug 4, 2026 by mohiso22 Contributor Loading…
Enable weightfree export with dynamo for Kimi K2.5
#1237 opened Aug 4, 2026 by quic-mamta Contributor Loading…
@quic-mamta
Fix for subfn, rope issue in Grok1
#1236 opened Aug 4, 2026 by tv-karthikeya Contributor • Draft
Fix KV cache handling for Gemma4 26B
#1235 opened Aug 4, 2026 by nsivalin Contributor • Draft
Fix CCL propagation for Gemma4 bidirectional-vision prefill
#1234 opened Aug 3, 2026 by vjanfaza Contributor Loading…
Add cohere_asr support - validated-hw on 4 QAIC AI100 devices
#1233 opened Aug 3, 2026 by mabusaa Loading…
Add pwrite-based single-file ONNX export + fix GPT-OSS dynamo export
#1232 opened Aug 3, 2026 by smedhe Contributor Loading…
GPT-OSS: Hoist Layer-Invariant Attention Mask Preparation Outside Decoder Subfunctions
#1231 opened Aug 2, 2026 by abhishek-singh591 Contributor Loading…
feat: add w_sub ONNX semantic weight + node rename transform
#1230 opened Jul 31, 2026 by vishwasdivakar Loading…
1
Head parallel and batch fold blocking for Qwen3-VL MOE
#1229 opened Jul 31, 2026 by kdulla Contributor • Draft
Fix for gemma4 sub-func and continous batching
#1224 opened Jul 30, 2026 by quic-hemagnih Contributor Loading…
feat(weight-free): weight-free ONNX export for causal LMs
#1220 opened Jul 27, 2026 by amarquic Loading…
27
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…
3
CI optimizations maintainer-approved-pyproject-change wip Work in progress
#1216 opened Jul 25, 2026 by quic-rishinr Contributor Loading…
@quic-rishinr
3
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…
69
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
Introducing OptimizedMoeTransform
#1190 opened Jul 17, 2026 by ochougul Contributor Loading…
6
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
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
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.