Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
339 Open 17,302 Closed
339 Open 17,302 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

[webgpu][dawn API optimization] make less call to wgpuDeviceHasFeature
#26474 opened Nov 1, 2025 by fs-eire Loading…
1
[QNN-EP] Disable DSPQ polling when needed
#26468 opened Nov 1, 2025 by quic-calvnguy Loading…
[node] remove incorrect error check
#26467 opened Nov 1, 2025 by fs-eire Loading…
1
Attenion(23) CUDA
#26466 opened Oct 31, 2025 by titaiwangms • Draft
1
[QNN-EP] Use same power votes as burst for SHP
#26465 opened Oct 31, 2025 by quic-calvnguy Loading…
[QNN-EP] Add skip_qnn_version_check option to QNN EP
#26464 opened Oct 31, 2025 by quic-muchhsu Loading…
Implement Split-K on Conv|MatMul
#26461 opened Oct 31, 2025 by Jiawei-Shao • Draft
4
[QNN-EP] - Tie HTP power config id lifetime to session
#26457 opened Oct 30, 2025 by quic-calvnguy Loading…
WeightBiasQuantization: fix expected axis for ConvTranspose
#26456 opened Oct 30, 2025 by qti-yuduo Loading…
2
[VitisAI EP] Fix error in graph resolving
#26452 opened Oct 30, 2025 by zpye Loading…
[WebGPU] Register DataTransfer to Env
#26450 opened Oct 30, 2025 by qjia7 • Draft
[Test Only] End profiling after 10 runs
#26449 opened Oct 30, 2025 by qjia7 • Draft
[webgpu] Fused SplitPackedQKV with FusedQKRotaryEmbedding ep:WebGPU ort-web webgpu provider
#26447 opened Oct 30, 2025 by xiaofeihan1 Loading…
[TRT/TRT RTX EP] Fix bug for missing outputs in the returning ComputeCapability/IndexedSubGraph
#26444 opened Oct 29, 2025 by chilo-ms Loading…
6
coreml: Fix Gather fp16 support
#26442 opened Oct 29, 2025 by borg323 Loading…
Add options to onnxruntime_perf_runner to externalize weights
#26441 opened Oct 29, 2025 by yuslepukhin Loading…
2
Allow get clip constant min/max from DequantizeLinear
#26438 opened Oct 29, 2025 by qti-yuduo Loading…
3
fix npm packaging
#26437 opened Oct 29, 2025 by guschmue Loading…
Generalize noop_with_empty_axes handling across all Reduce operators
#26436 opened Oct 29, 2025 by naomiOvad Loading…
1
4
[VitisAI]add tensor type bool
#26434 opened Oct 29, 2025 by BoarQing Loading…
1
webgpu: optimize Gemm and MatMul using subgroup feature ep:WebGPU ort-web webgpu provider
#26433 opened Oct 29, 2025 by xhcao Loading…
5
[webgpu] revise implementation of buffer split support ep:WebGPU ort-web webgpu provider
#26429 opened Oct 29, 2025 by fs-eire Loading…
12
[WIP][webgpu] optimize emscripten inter-op for buffer
#26427 opened Oct 28, 2025 by fs-eire • Draft
6
[TRT RTX EP] Enable double datatype for intermediate nodes
#26423 opened Oct 28, 2025 by thevishalagarwal Loading…
3
[QNN EP] Fuse Gelu pattern into a QNN Gelu Node
#26417 opened Oct 27, 2025 by quic-tirupath Loading…
11
ProTip! Filter pull requests by the default branch with base:main.