Skip to content

Pull requests: huggingface/optimum-executorch

New pull request New
25 Open 150 Closed
25 Open 150 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

fix: auto-disable dynamic shapes when custom KV cache is enabled
#235 opened Jun 24, 2026 by psiddh Loading…
Small typo in top level README
#234 opened Jun 23, 2026 by JakeStevens Loading…
chore: enable Dependabot weekly GitHub Actions bumps dependabot
#231 opened May 26, 2026 by hf-dependantbot-rollout Bot Loading…
Fix T5 export: encoder attention mask and static decoder shapes
#230 opened Apr 20, 2026 by duyhv-qualgo Loading…
Expose --quantize_dtype CLI arg to control dtype during quantization
#228 opened Apr 13, 2026 by rhn19 Loading…
1
Expose --qparams_algorithm CLI arg for quantization parameter selection
#227 opened Apr 13, 2026 by rhn19 Loading…
1
[DO NOT LAND] Add linear+bias decomposition
#222 opened Mar 13, 2026 by manuelcandales Contributor Loading…
Add SDPA decomposition for Metal backend with unsupported head_dim
#221 opened Mar 2, 2026 by seyeong-han Contributor Loading…
Fix: respect --max_seq_len for sliding window models with custom kv cache + sdpa
#219 opened Feb 20, 2026 by rhn19 Loading…
1
1
Fix crash after failed audio download in process_conversation_inputs
#217 opened Feb 20, 2026 by kirklandsign Loading…
Fix broken error handling for unregistered task/recipe lookup
#216 opened Feb 20, 2026 by kirklandsign Loading…
Add Attention sink in export
#215 opened Feb 20, 2026 by kirklandsign Loading…
1
Add Qwen3-VL export support for multimodal text-to-text pipeline
#214 opened Feb 19, 2026 by seyeong-han Contributor Loading…
Enable re-inplace pass in XNNPACK recipe
#213 opened Feb 13, 2026 by GregoryComer • Draft
Support max_seq_len argument in multimodal text-to-text export
#209 opened Feb 1, 2026 by kamalkraj Loading…
Upgrade GitHub Actions for Node 24 compatibility
#198 opened Dec 20, 2025 by salmanmkc Loading…
[NOT FOR LAND] init work for registering custom triton kernel
#186 opened Nov 12, 2025 by Gasoonjia Contributor Loading…
Vulkan recipe
#183 opened Nov 10, 2025 by larryliu0820 Collaborator • Draft
gemma3 model on et-cuda backend
#169 opened Oct 16, 2025 by Gasoonjia Contributor Loading…
3
[not for commit] test gemma3
#155 opened Sep 29, 2025 by metascroy Contributor Loading…
Add qnn recipe
#121 opened Aug 6, 2025 by cccclai Loading…
5
Support image-text-to-text task
#111 opened Jul 23, 2025 by larryliu0820 Collaborator Loading…
47
Add resnet50 to supported models
#90 opened Jun 24, 2025 by metascroy Contributor Loading…
3
[not for landing/review] coreml ga testing
#76 opened Jun 6, 2025 by metascroy Contributor Loading…
3
[not to merge] executorch.export recipe integration
#71 opened May 30, 2025 by tarun292 • Draft
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.