Skip to content

Pull requests: quic/efficient-transformers

New pull request New
56 Open 1,098 Closed
56 Open 1,098 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

Add reported reproducer config test suite
#1173 opened Jul 10, 2026 by anujgupt-github Contributor Loading…
[nightly] Fix garbage output in VLM nightly tests
#1172 opened Jul 10, 2026 by quic-vishali Contributor • Draft
Updating blocking dummy tests qeff.blocking
#1171 opened Jul 10, 2026 by kdulla Contributor Loading…
@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
feat: dynamo-based ONNX export with subfunction support for CausalLM models 1.23 Release 1.23 Features enhancement New feature or request onnx.dynamo
#1169 opened Jul 9, 2026 by smedhe Contributor Loading…
@vbaddi @smedhe
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…
3
Enabling model Qwen3-Embedding-0.6B and Qwen3-Embedding-8B
#1151 opened Jul 6, 2026 by quic-amitraj Contributor • Draft
Disagg serving with efficient KV handoff
#1150 opened Jul 6, 2026 by quic-akuruvil Contributor Loading…
Updated Default AIC hardware detection to NSP IMAGE_VARIANT
#1147 opened Jul 3, 2026 by asmigosw Contributor Loading…
Pytest for Qwen3 VL disagg mode 3 qpc
#1145 opened Jul 2, 2026 by tv-karthikeya Contributor Loading…
1
Make dataPathTimeoutMs configurable, default 120s
#1142 opened Jun 30, 2026 by quic-rishinr Contributor • Draft
4
Added multi resolution support for qwen models on 1.22.0_tf_4.57.3 branch
#1141 opened Jun 30, 2026 by quic-rishinr Contributor Loading…
7
Add skills_studio/skills/qeff-pr-reviewer
#1139 opened Jun 29, 2026 by quic-rishinr Contributor Loading…
Add MDP strategy guidance
#1138 opened Jun 29, 2026 by quic-mohmeh Contributor Loading…
8
added basic NPI generation skill
#1137 opened Jun 29, 2026 by ochougul Contributor Loading…
Revert the pkv_in_bfloat16 variable to its previous state
#1134 opened Jun 27, 2026 by tchawada Contributor Loading…
Updated example file for ai200 runs
#1127 opened Jun 25, 2026 by asmigosw Contributor • Draft
Make num_cores (NSP) configurable via NUM_CORES env for nightly pipeline
#1117 opened Jun 24, 2026 by quic-vishali Contributor Loading…
RepeatKV Transform changes with comments addressed
#1114 opened Jun 24, 2026 by quic-dhirajku Contributor Loading…
7
Reduce CI model test matrix runtime
#1111 opened Jun 23, 2026 by ochougul Contributor • Draft
1
Add Support for Kimi K2.5 Vision
#1108 opened Jun 22, 2026 by quic-mamta Contributor • Draft
@quic-mamta
fix(mixtral): fix MXFP6 quantization and ONNX export issues for Mixtral_moe
#1107 opened Jun 22, 2026 by Cs23m011 Loading…
1
Added fix to layerwise implementation to incorporate CB
#1106 opened Jun 22, 2026 by abhishek-singh591 Contributor Loading…
17
[Nightly-CI-Summary]: Adding nightly summary report
#1103 opened Jun 19, 2026 by abukhoy Contributor • Draft
Feature/add minimax m3 vl
#1096 opened Jun 18, 2026 by shagsood • Draft
ProTip! Adding no:label will show everything without a label.