Skip to content

Actions: microsoft/onnxruntime

Actions

CodeQL

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
codeql.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[Build] Use H100 instead of A10 pool for CI CodeQL #56651: Pull request #32664 synchronize by tianleiwu
5m 45s tlwu/20260916/ci_h100
tlwu/20260916/ci_h100
5m 45s
[Build] Use H100 instead of A10 pool for CI CodeQL #56650: Pull request #32664 opened by tianleiwu
2m 29s tlwu/20260916/ci_h100
tlwu/20260916/ci_h100
2m 29s
[WebNN EP] Support GroupNormalization, GroupNorm and SkipGroupNorm CodeQL #56649: Pull request #32606 synchronize by Honry
Action required Honry:groupNorm
Honry:groupNorm
Action required
Skip redundant present_key/value copy when aliased to external KV cache (follow-up to #29715) CodeQL #56648: Pull request #31150 synchronize by titaiwangms
5m 48s copilot/cudnn-sdpa-decode-phase3
copilot/cudnn-sdpa-decode-phase3
5m 48s
Enable opt-in host-pageable CUDA GatherBlockQuantized CodeQL #56647: Pull request #32626 synchronize by Copilot AI
5m 31s copilot/enable-opt-in-gather-block-quantized
copilot/enable-opt-in-gather-block-quantized
5m 31s
[WebGPU] checks to handle oob writes based on seqlens_k CodeQL #56646: Pull request #32623 synchronize by edgchen1
5m 28s edgchen1/wgpu-gqa-oob-write
edgchen1/wgpu-gqa-oob-write
5m 28s
Limit AOT function expansion CodeQL #56645: Pull request #32662 opened by apsonawane
5m 52s fix/limit-aot-function-expansion
fix/limit-aot-function-expansion
5m 52s
Integrate ONNX 1.23.0 base plumbing CodeQL #56644: Pull request #32359 synchronize by justinchuby
5m 37s justinchuby-onnx-1-23-opset-28-base
justinchuby-onnx-1-23-opset-28-base
5m 37s
Fix WebNN ConvTranspose shape arithmetic overflow CodeQL #56643: Pull request #32661 opened by edgchen1
2m 13s edgchen1/fix_conv_transpose_overflow
edgchen1/fix_conv_transpose_overflow
2m 13s
Fix: LayerNormFusion should reject shape-expanding scale and bias patterns CodeQL #56642: Pull request #32660 synchronize by SIDDARTHAREDDY8
Action required SIDDARTHAREDDY8:oss-bhai-2026-09-16b
SIDDARTHAREDDY8:oss-bhai-2026-09-16b
Action required
Fix: LayerNormFusion should reject shape-expanding scale and bias patterns CodeQL #56641: Pull request #32660 synchronize by SIDDARTHAREDDY8
Action required SIDDARTHAREDDY8:oss-bhai-2026-09-16b
SIDDARTHAREDDY8:oss-bhai-2026-09-16b
Action required
Fix: LayerNormFusion should reject shape-expanding scale and bias patterns CodeQL #56640: Pull request #32660 opened by SIDDARTHAREDDY8
Action required SIDDARTHAREDDY8:oss-bhai-2026-09-16b
SIDDARTHAREDDY8:oss-bhai-2026-09-16b
Action required
Add BF16 routing support to CUDA MoE CodeQL #56639: Pull request #32659 synchronize by kunal-vaishnavi
5m 39s kvaishnavi/moe-bf16-cuda
kvaishnavi/moe-bf16-cuda
5m 39s
Validate packed GQA head counts during shape inference CodeQL #56638: Pull request #32658 synchronize by danielsongmicrosoft
Action required danielsongmicrosoft:user/danielsong/validate-packed-gqa-head-counts
danielsongmicrosoft:user/danielsong/validate-packed-gqa-head-counts
Action required
Add GQA workspace estimation CodeQL #56637: Pull request #32617 synchronize by titaiwangms
6m 0s titaiwangms:titaiwangms/gqa-workspace-estimation
titaiwangms:titaiwangms/gqa-workspace-estimation
6m 0s
Add BF16 routing support to CUDA MoE CodeQL #56636: Pull request #32659 opened by kunal-vaishnavi
6m 38s kvaishnavi/moe-bf16-cuda
kvaishnavi/moe-bf16-cuda
6m 38s
Integrate ONNX 1.23.0 base plumbing CodeQL #56635: Pull request #32359 synchronize by justinchuby
5m 57s justinchuby-onnx-1-23-opset-28-base
justinchuby-onnx-1-23-opset-28-base
5m 57s
Optimize CUDA QSA sparse attention indexing CodeQL #56634: Pull request #32656 synchronize by Copilot AI
6m 2s copilot/copilotcopilotimplement-packed-sparse-attention-in
copilot/copilotcopilotimplement-packed-sparse-attention-in
6m 2s
[WebGPU] checks to handle oob writes based on seqlens_k CodeQL #56633: Pull request #32623 synchronize by edgchen1
5m 49s edgchen1/wgpu-gqa-oob-write
edgchen1/wgpu-gqa-oob-write
5m 49s
Add GQA workspace estimation CodeQL #56632: Pull request #32617 synchronize by titaiwangms
5m 56s titaiwangms:titaiwangms/gqa-workspace-estimation
titaiwangms:titaiwangms/gqa-workspace-estimation
5m 56s
[CUDA][WebGPU] Add packed sparse attention indexer for continuous batching CodeQL #56631: Pull request #32618 synchronize by Copilot AI
5m 40s copilot/copilotimplement-packed-sparse-attention-indexer
copilot/copilotimplement-packed-sparse-attention-indexer
5m 40s
Validate packed GQA head counts during shape inference CodeQL #56630: Pull request #32658 opened by danielsongmicrosoft
Action required danielsongmicrosoft:user/danielsong/validate-packed-gqa-head-counts
danielsongmicrosoft:user/danielsong/validate-packed-gqa-head-counts
Action required
Add GQA workspace estimation CodeQL #56629: Pull request #32617 synchronize by titaiwangms
5m 35s titaiwangms:titaiwangms/gqa-workspace-estimation
titaiwangms:titaiwangms/gqa-workspace-estimation
5m 35s
Add GQA workspace estimation CodeQL #56628: Pull request #32617 synchronize by titaiwangms
5m 42s titaiwangms:titaiwangms/gqa-workspace-estimation
titaiwangms:titaiwangms/gqa-workspace-estimation
5m 42s
2bit 6bit quantization exploration CodeQL #56627: Pull request #32657 synchronize by jiafatom
2m 5s jiafa/2bit-6bit-quantization-exploration
jiafa/2bit-6bit-quantization-exploration
2m 5s