Skip to content

Pull requests: microsoft/onnxruntime

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

Add INT4 per-channel MoE GEMV fast path for batch-1 decode
#29038 opened Jun 13, 2026 by tianleiwu Contributor Loading…
Bump esbuild, @vitejs/plugin-vue and vite in /js/web/test/e2e/exports/testcases/vite-default dependencies Pull requests that update a dependency file javascript Pull requests that update Javascript code
#29036 opened Jun 13, 2026 by dependabot Bot Loading…
Plugin WebGPU EP Branch: Update protobufjs versions
#29031 opened Jun 12, 2026 by adrastogi Contributor Loading…
Fix WebGPU GatherBlockQuantized dispatch failure for empty indices
#29030 opened Jun 12, 2026 by tairenpiao Contributor Loading…
[CUDA] QMoE support shared experts
#29028 opened Jun 12, 2026 by tianleiwu Contributor Draft
[ORT] Extend reshape fusion
#29027 opened Jun 12, 2026 by Honry Contributor Loading…
[WebNN EP] Support 8-bit MatMulNBits
#29025 opened Jun 12, 2026 by Honry Contributor Loading…
[WebNN EP] Remove unnecessary cast around normalization ops
#29024 opened Jun 12, 2026 by Honry Contributor Loading…
Fix ToOrtStatus translation of SYSTEM-category Status error codes
#29023 opened Jun 12, 2026 by edgchen1 Contributor Loading…
[WebGPU] Fix profiling timestamp alignment with ORT profiler
#29021 opened Jun 12, 2026 by daijh Contributor Loading…
Bump joi and react-native in /js/react_native/e2e dependencies Pull requests that update a dependency file javascript Pull requests that update Javascript code
#29019 opened Jun 11, 2026 by dependabot Bot Loading…
[js/web] Forward WebGPU EP buffer cache mode options from JS
#29017 opened Jun 11, 2026 by ssam18 Contributor Loading…
Fix rotary embedding oob issue
#29014 opened Jun 11, 2026 by apsonawane Contributor Loading…
Fix arbitrary memory read
#29011 opened Jun 11, 2026 by apsonawane Contributor Loading…
Fixed failing KleidiAI NHWC unit tests
#29010 opened Jun 11, 2026 by martin-klacer-arm Loading…
Fix libatomic linking on toolchains that default to ld --as-needed
#29008 opened Jun 11, 2026 by ssam18 Contributor Loading…
webgpu: fix GQA batched right-padded prefill with do_rotary
#29002 opened Jun 11, 2026 by qjia7 Contributor Loading…
7 tasks done
[WebGPU] Graph capture support for KV-shared decoder models ep:WebGPU ort-web webgpu provider
#29000 opened Jun 11, 2026 by feich-ms Contributor Draft
4 tasks
Bump torch from 2.7.0 to 2.12.0 in /onnxruntime/python/tools/transformers/models/whisper dependencies Pull requests that update a dependency file python Pull requests that update Python code
#28993 opened Jun 10, 2026 by dependabot Bot Loading…
[CUDA] Add decode (M=1) GEMV fast path to MatMul
#28986 opened Jun 10, 2026 by tianleiwu Contributor Loading…
[CUDA] Add decode-optimized LinearAttention (GatedDeltaNet) kernels
#28985 opened Jun 10, 2026 by tianleiwu Contributor Loading…
ProTip! Updated in the last three days: updated:>2026-06-10.