-
Notifications
You must be signed in to change notification settings - Fork 3.9k
Pull requests: microsoft/onnxruntime
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
QMoE CUDA: Rename build options, refactor PrePack, add GPU kernels
#28583
opened May 20, 2026 by
tianleiwu
Contributor
Loading…
[WebGPU] Avoid indirect dispatch in FlashAttention decode to fix perf issues with Vulkan backend + GraphCapture/GraphReplay
ep:WebGPU
ort-web webgpu provider
#28581
opened May 20, 2026 by
hariharans29
Member
Loading…
Add linux-arm64 binaries to the foundry nuget package
#28579
opened May 20, 2026 by
baijumeswani
Contributor
Loading…
CPU GroupQueryAttention: Quantized KV Cache with SIMD-optimized MLAS kernels
#28578
opened May 20, 2026 by
tianleiwu
Contributor
Loading…
Bump protobufjs from 7.2.5 to 7.5.8 in /js/web
dependencies
Pull requests that update a dependency file
javascript
Pull requests that update Javascript code
#28573
opened May 19, 2026 by
dependabot
Bot
Loading…
[MLAS] Update the NHWC sans transposes path to also support Depthwise convolutions
#28565
opened May 19, 2026 by
orlmon01
Contributor
Loading…
TurboQuant KV cache (4/4): Python reference impl + last_token_logits patcher
#28563
opened May 19, 2026 by
TimPietrusky
•
Draft
TurboQuant KV cache (3/4): WebGPU kernels + Safari/Firefox fallback
#28562
opened May 19, 2026 by
TimPietrusky
•
Draft
TurboQuant KV cache (1/4): graph rewrite + schema (foundation)
#28560
opened May 19, 2026 by
TimPietrusky
•
Draft
Raise protobuf minimum version in Python requirements
#28558
opened May 19, 2026 by
anzzraju1997-glitch
Loading…
Skip SetupDi device discovery if Win32k system calls are disabled
#28535
opened May 18, 2026 by
shiyi9801
Contributor
Loading…
fix(cann): prevent race condition on .om cache file during multi-card compilation
#28533
opened May 17, 2026 by
0AnshuAditya0
Loading…
Update GatherBlockQuantized to support 2-bits
ep:WebGPU
ort-web webgpu provider
#28530
opened May 16, 2026 by
HectorSVC
Contributor
Loading…
Update microsoft_gsl from v4.0.0 to v4.2.1 (fixes C4875 deprecation)
#28527
opened May 15, 2026 by
Copilot
AI
Loading…
[WebGPU plugin EP] Add Win ARM64 Python package
plugin-ep-webgpu/release:0.1.0
#28526
opened May 15, 2026 by
edgchen1
Contributor
Loading…
Check weight shape dimensions in ConvTranspose shape inference msrc116345
#28524
opened May 15, 2026 by
yuslepukhin
Member
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-04-20.