Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
870 Open 19,650 Closed
870 Open 19,650 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 TensorRT engine cache shape collisions
#32563 opened Sep 11, 2026 by Aziz Muminov (AzizMuminov) Loading…
1
2
Add CPU fp16 insert-cast policy controls
#32562 opened Sep 11, 2026 by patryk-kaiser-ARM Contributor Loading…
4
[WebGPU] Support QuickGelu activation in the im2col-matmul path
#32560 opened Sep 11, 2026 by xhcao Contributor Loading…
4
[CUDA] Guard FP8 XQA test by compute capability
#32559 opened Sep 11, 2026 by Tianlei Wu (tianleiwu) Contributor Loading…
1
Validate NCHWc convolution layouts
#32557 opened Sep 10, 2026 by Akshay Sonawane (apsonawane) Contributor Loading…
3
Validate LayerNormalization axis bounds
#32555 opened Sep 10, 2026 by Akshay Sonawane (apsonawane) Contributor Loading…
2
Validate AllGather shape attributes
#32554 opened Sep 10, 2026 by Akshay Sonawane (apsonawane) Contributor Loading…
2
Fix heap overflow
#32553 opened Sep 10, 2026 by Akshay Sonawane (apsonawane) Contributor Loading…
1
Validate NCHWc reorder channel layout
#32552 opened Sep 10, 2026 by Akshay Sonawane (apsonawane) Contributor Loading…
2
Validate CUDA Split dimension products
#32551 opened Sep 10, 2026 by Akshay Sonawane (apsonawane) Contributor Loading…
2
[objc docs] Fix doc generation workflow
#32550 opened Sep 10, 2026 by Edward Chen (edgchen1) Contributor Loading…
2
Add contributor sorting option to compile_contributors.py
#32549 opened Sep 10, 2026 by Tianlei Wu (tianleiwu) Contributor Loading…
1
Support RTX 50-series GPUs in Linux CUDA Docker builds
#32548 opened Sep 10, 2026 by Copilot AI • Draft
1
@tianleiwu
1
Restrict XQA CUDA compilation to SM80 and newer
#32547 opened Sep 10, 2026 by Copilot AI • Draft
1
@tianleiwu
1
Reject zero divisors in CUDA Mod kernels
#32546 opened Sep 10, 2026 by Copilot AI • Draft
1
@tianleiwu
1
Prevent POSIX telemetry crash in shell-less containers
#32545 opened Sep 10, 2026 by Copilot AI • Draft
1
@tianleiwu
2
Detect Jetson GPUs in Linux DRM device discovery
#32544 opened Sep 10, 2026 by Copilot AI • Draft
1
@tianleiwu
1
Fix localized DirectML adapter errors in Python
#32543 opened Sep 10, 2026 by Aziz Muminov (AzizMuminov) Loading…
1
4
[MLAS] Riscv64 rvv kernel optimizations
#32540 opened Sep 10, 2026 by Zestion Contributor Loading…
7
Preserve negative zero in CPU Where
#32539 opened Sep 10, 2026 by Sylvester Kaczmarek (sylvesterkaczmarek) Contributor Loading…
1
6
Avoid telemetry session sidecar for in-memory storage
#32538 opened Sep 10, 2026 by Sylvester Kaczmarek (sylvesterkaczmarek) Contributor Loading…
1
4
[WebGPU] Add SparsePagedAttention
#32533 opened Sep 10, 2026 by Copilot AI • 2/2 Loading…
@kunal-vaishnavi
2
Fix duplicate script_params in the AzureML BERT notebook
#32532 opened Sep 10, 2026 by David Wu (David-Wu1119) Loading…
2
[WebGPU] Add DynamicSparseAttention
#32529 opened Sep 10, 2026 by Copilot AI • 2/2 Loading…
@kunal-vaishnavi
10
[WebGPU] Implement SparseAttentionIndexer operator
#32528 opened Sep 10, 2026 by Copilot AI • 2/2 Loading…
@kunal-vaishnavi
10
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.