Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
329 Open 17,227 Closed
329 Open 17,227 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

[Build] New docker image with GCC 14 and CUDA 12.8/13.0
#26349 opened Oct 18, 2025 by tianleiwu • Draft
[QNN-EP] Add documentation for optrace profiling
#26348 opened Oct 18, 2025 by quic-calvnguy Loading…
ORT 1.23.2 cherrypick 1
#26347 opened Oct 17, 2025 by apsonawane Loading…
1
[build] disable DAWN_FETCH_DEPENDENCIES when using custom dawn src path
#26346 opened Oct 17, 2025 by fs-eire Loading…
Save much memory at model loading time by converting weights to OrtValues early
#26345 opened Oct 17, 2025 by yuslepukhin Loading…
1
Enable onnxruntime_autoep_test on Android
#26344 opened Oct 17, 2025 by edgchen1 • Draft
2
[TRT RTX EP] Add Pipelines
#26343 opened Oct 17, 2025 by chilo-ms • Draft
VitisAI bugfix model clone optimization2
#26342 opened Oct 17, 2025 by abalasa-amd Loading…
1
[QNN EP] Enable v81 devices
#26341 opened Oct 17, 2025 by qti-jkilpatrick Loading…
5
[QNN-EP] Add MatMulNBits translation for GPU
#26340 opened Oct 17, 2025 by quic-tirupath Loading…
12
[QNN EP] Relax checkShape for Batch Multiplier
#26336 opened Oct 17, 2025 by chunghow-qti Loading…
1
[webgpu] Fused GeneratePositionIDs into FusedQKRotaryEmbedding ep:WebGPU ort-web webgpu provider
#26335 opened Oct 17, 2025 by xiaofeihan1 Loading…
[webgpu] Don't use num_workgroups when use indirect dispatch
#26334 opened Oct 17, 2025 by qjia7 Loading…
2
[QNN EP] Fuse Gelu pattern into a QNN Gelu Node
#26332 opened Oct 17, 2025 by quic-tirupath Loading…
4
[QNN-EP] Implement ABI methods for model compatibility
#26331 opened Oct 16, 2025 by quic-calvnguy • Draft
[WebGPU] allows user to specify high-performance or low-power preference
#26326 opened Oct 16, 2025 by prathikr Loading…
feat: Add BFloat16 support for Gemm and MatMul CPU operators
#26317 opened Oct 15, 2025 by snnn Loading…
1
20
Use time_costs_total for output_stats
#26313 opened Oct 15, 2025 by keshavv27 Loading…
2
docs: update EP support table
#26310 opened Oct 15, 2025 by nekomeowww Loading…
1
[WebNN] Fallback int64 indices to int32
#26308 opened Oct 15, 2025 by Honry Loading…
30
[CUDA] Adjust package build settings for Blackwell GPU
#26307 opened Oct 14, 2025 by tianleiwu • Draft
Address MLAS NchwcBlockSize for AMD64 platforms behavior in the minimal builds
#26306 opened Oct 14, 2025 by yuslepukhin Loading…
10
fix npm publishing
#26305 opened Oct 14, 2025 by guschmue Loading…
2
Allow present_key to be empty when past_key is provided in Attention
#26303 opened Oct 14, 2025 by justinchuby Loading…
6
Implement FP32 kleidiai Gemv
#26302 opened Oct 14, 2025 by JonathanC-ARM Loading…
4
ProTip! Add no:assignee to see everything that’s not assigned.