Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
4c184ac
Add opset 28 SpaceToDepth support (#32362)
justinchuby Oct 20, 2026
786177a
cuda pagedattention seqlens shape fix (#31651)
apsonawane Oct 20, 2026
a243f8c
Validate PackedAttention token offsets (#33330)
apsonawane Oct 20, 2026
942356f
[CUDA] Add fused decode routing, single-pass finalize, and PDL overla…
tianleiwu Oct 20, 2026
53e61f3
Update transformers and FlatBuffers Go example grpc dependency pins (…
mustjab Oct 21, 2026
fb8bfaa
[WebGPU] Package D3D12 Agility SDK for Python wheels (#32795)
mei1127 Oct 21, 2026
6a5a08c
[WebGPU] Automate Dawn updates (#33396)
gyagp Oct 21, 2026
973f680
[CICD Stability] Start transition to scaleset based providers (#33492)
eserscor Oct 21, 2026
b923407
Validate ORT format edge slots (#32200)
apsonawane Oct 21, 2026
c55286e
Fix correctness guards in training graph optimizers (#32982)
Yuhx141 Oct 21, 2026
314ff8d
[Framework/CUDA] Add generic kernel dispatch policy reader (#33042)
chilo-ms Oct 21, 2026
8b17e67
[WebGPU] Add bit-exact convolution state replay for speculative decod…
aciddelgado Oct 21, 2026
db5f5ea
Fix Gemm transpose fusion with public input outputs (#33484)
xgbtxy Oct 21, 2026
a926b83
Fix CUDA LayerNorm/RMSNorm silent wrong output for rank-reduced scale…
justinchuby Oct 21, 2026
f7b31b7
[CUDA] Cosmos3 - Fix variance cancellation in fused BERT layer normal…
rui-ren Oct 21, 2026
c33b4eb
Avoid quadratic allocation-planner free-buffer scans (#33407)
rui-ren Oct 21, 2026
ed8f79b
[CUDA] Honor deterministic compute for MatMulNBits tactic selection (…
kunal-vaishnavi Oct 21, 2026
219e109
Merge remote-tracking branch 'origin/master' into sync_msft_22102026
AIFrameworksIntegration Oct 21, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 3 additions & 15 deletions .github/workflows/android.yml
Original file line number Diff line number Diff line change
Expand Up @@ -24,11 +24,7 @@ permissions:

jobs:
AndroidBinarySizeCheckJob_MinimalBaseline:
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=AndroidBinarySizeCheckJob_MinimalBaseline-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
env:
CCACHE_DIR: ~/.cache/ccache # explicitly set to prevent any fallback to `~/.ccache`
Expand Down Expand Up @@ -119,11 +115,7 @@ jobs:
shell: bash

android_nnapi_ep:
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=android_nnapi_ep-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
env:
CCACHE_DIR: ~/.cache/ccache # explicitly set to prevent any fallback to `~/.ccache`
Expand Down Expand Up @@ -234,11 +226,7 @@ jobs:

android_cpu_ep:
name: Android CI Pipeline
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=android_cpu_ep-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
env:
CCACHE_DIR: ~/.cache/ccache # explicitly set to prevent any fallback to `~/.ccache`
Expand Down
6 changes: 1 addition & 5 deletions .github/workflows/cffconvert.yml
Original file line number Diff line number Diff line change
Expand Up @@ -9,11 +9,7 @@ on:
jobs:
validate:
name: "validate"
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=cffconvert-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
steps:
- name: Check out a copy of the repository
Expand Down
6 changes: 1 addition & 5 deletions .github/workflows/codeql.yml
Original file line number Diff line number Diff line change
Expand Up @@ -23,11 +23,7 @@ concurrency:
jobs:
analyze:
name: Analyze
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=codeql-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}-${{ matrix.language}}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions:
actions: read
Expand Down
6 changes: 1 addition & 5 deletions .github/workflows/gradle-wrapper-validation.yml
Original file line number Diff line number Diff line change
Expand Up @@ -13,11 +13,7 @@ on:
jobs:
validation:
name: "Validation"
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=gradle-wrapper-validation-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
steps:
- uses: actions/checkout@d23441a48e516b6c34aea4fa41551a30e30af803 # v6.1.0
Expand Down
6 changes: 1 addition & 5 deletions .github/workflows/labeler.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,11 +8,7 @@ permissions:

jobs:
triage:
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=labeler-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
steps:
- uses: github/issue-labeler@ccca1e16fcb66762200e616fc29b57b940c1cb67 # v3.5
Expand Down
6 changes: 1 addition & 5 deletions .github/workflows/lint.yml
Original file line number Diff line number Diff line change
Expand Up @@ -39,11 +39,7 @@ jobs:
lint-python-format:
# Required workflow
name: Python format
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=lint-python-format-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions:
contents: read
Expand Down
6 changes: 1 addition & 5 deletions .github/workflows/linux-wasm-ci-build-and-test-workflow.yml
Original file line number Diff line number Diff line change
Expand Up @@ -41,11 +41,7 @@ on:

jobs:
build-wasm:
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-linux-large",
"JobId=build-wasm-${{inputs.job_name}}-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-32-amd-scus-ss]
timeout-minutes: 120
env:
buildArch: x64
Expand Down
14 changes: 7 additions & 7 deletions .github/workflows/linux_ci.yml
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ jobs:
name: Build Linux x64 Debug (ASan)
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU"
pool_name: "ort-github-linux-16-amd-wcus-ss"
build_config: Debug
architecture: x64
dockerfile_path: tools/ci_build/github/linux/docker/inference/x86_64/default/cpu/Dockerfile
Expand All @@ -58,7 +58,7 @@ jobs:
name: Build Linux x64 Release
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU"
pool_name: "ort-github-linux-16-amd-wcus-ss"
build_config: Release
architecture: x64
dockerfile_path: tools/ci_build/github/linux/docker/Dockerfile.manylinux2_28_cpu
Expand All @@ -74,7 +74,7 @@ jobs:
name: Build Linux x64 Release (Python 3.14)
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU"
pool_name: "ort-github-linux-16-amd-wcus-ss"
build_config: Release
architecture: x64
dockerfile_path: tools/ci_build/github/linux/docker/Dockerfile.manylinux2_28_cpu
Expand All @@ -93,7 +93,7 @@ jobs:
name: Build Linux x64 Release with training
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU"
pool_name: "ort-github-linux-16-amd-wcus-ss"
build_config: Release
architecture: x64
dockerfile_path: tools/ci_build/github/linux/docker/Dockerfile.manylinux2_28_cpu
Expand All @@ -108,7 +108,7 @@ jobs:
name: Build Linux x64 MinSizeRel (Exceptions Disabled)
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU"
pool_name: "ort-github-linux-16-amd-wcus-ss"
build_config: MinSizeRel
architecture: x64
dockerfile_path: tools/ci_build/github/linux/docker/inference/x86_64/default/cpu/Dockerfile
Expand All @@ -125,7 +125,7 @@ jobs:
name: Build Linux arm64 Debug
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-ARM-CPU"
pool_name: "ort-github-linux-16-arm64-eus2-ss"
build_config: Debug
architecture: arm64
dockerfile_path: tools/ci_build/github/linux/docker/inference/aarch64/default/cpu/Dockerfile
Expand All @@ -140,7 +140,7 @@ jobs:
name: Build Linux arm64 Release
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-ARM-CPU"
pool_name: "ort-github-linux-16-arm64-eus2-ss"
build_config: Release
architecture: arm64
dockerfile_path: tools/ci_build/github/linux/docker/inference/aarch64/python/cpu/Dockerfile
Expand Down
7 changes: 2 additions & 5 deletions .github/workflows/linux_cuda_ci.yml
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ jobs:
# This job runs on a CPU node using the reusable build workflow
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU" # Build pool
pool_name: "ort-github-linux-16-amd-wcus-ss" # Build pool
build_config: Release
architecture: x64
dockerfile_path: tools/ci_build/github/linux/docker/Dockerfile.manylinux2_28_cuda
Expand Down Expand Up @@ -55,10 +55,7 @@ jobs:
test-linux-cuda-x64-release:
name: Test Linux CUDA x64 Release
needs: build-linux-cuda-x64-release
runs-on:
- self-hosted
- "1ES.Pool=onnxruntime-github-linux-a10"
- "JobId=test-linux-cuda-x64-release-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
runs-on: [ort-github-linux-6-a10-scus-ss]
timeout-minutes: 210
permissions:
contents: read
Expand Down
7 changes: 2 additions & 5 deletions .github/workflows/linux_cuda_no_cudnn.yml
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ jobs:
name: Build Linux CUDA x64 Release without cuDNN link
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU"
pool_name: "ort-github-linux-16-amd-wcus-ss"
build_config: Release
architecture: x64
dockerfile_path: tools/ci_build/github/linux/docker/Dockerfile.manylinux2_28_cuda
Expand Down Expand Up @@ -57,10 +57,7 @@ jobs:
smoke-linux-cuda-no-cudnn-x64-release:
name: Smoke Linux CUDA x64 Release without cuDNN runtime use
needs: build-linux-cuda-no-cudnn-x64-release
runs-on:
- self-hosted
- "1ES.Pool=onnxruntime-github-linux-a10"
- "JobId=smoke-linux-cuda-no-cudnn-x64-release-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
runs-on: [ort-github-linux-6-a10-scus-ss]
timeout-minutes: 210
permissions:
contents: read
Expand Down
7 changes: 2 additions & 5 deletions .github/workflows/linux_cuda_plugin_ci.yml
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ jobs:
name: Build Linux CUDA Plugin EP x64 Release
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU" # Build pool
pool_name: "ort-github-linux-16-amd-wcus-ss" # Build pool
build_config: Release
architecture: x64
dockerfile_path: tools/ci_build/github/linux/docker/Dockerfile.manylinux2_28_cuda
Expand Down Expand Up @@ -54,10 +54,7 @@ jobs:
test-linux-cuda-plugin-x64-release:
name: Test Linux CUDA Plugin EP x64 Release
needs: build-linux-cuda-plugin-x64-release
runs-on:
- self-hosted
- "1ES.Pool=onnxruntime-github-linux-a10"
- "JobId=test-linux-cuda-plugin-x64-release-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
runs-on: [ort-github-linux-6-a10-scus-ss]
timeout-minutes: 210
permissions:
contents: read
Expand Down
60 changes: 10 additions & 50 deletions .github/workflows/linux_minimal_build.yml
Original file line number Diff line number Diff line change
Expand Up @@ -22,11 +22,7 @@ jobs:
# Job 1: Build full onnxruntime and generate ORT format test files
build_full_ort:
name: 1. Build Full ORT and Generate ORT Files
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_full_ort-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions:
contents: read
Expand Down Expand Up @@ -86,11 +82,7 @@ jobs:
# Job 2: Build minimal onnxruntime [exceptions DISABLED, type reduction DISABLED, training ops ENABLED]
build_minimal_exceptions_disabled:
name: 2. Build Minimal (Exceptions Disabled)
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_minimal_exceptions_disabled-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions: # Permissions needed for build-docker-image
contents: read
Expand Down Expand Up @@ -163,11 +155,7 @@ jobs:
build_minimal_custom_ops:
name: 3a. Build Minimal (Custom Ops)
needs: build_full_ort # Depends on Job 1 for test data
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_minimal_custom_ops-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions: # Permissions needed for build-docker-image
contents: read
Expand Down Expand Up @@ -219,11 +207,7 @@ jobs:
build_minimal_type_reduction:
name: 3b. Build Minimal (Type Reduction)
needs: build_full_ort # Depends on Job 1 for test data
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_minimal_type_reduction-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions: # Permissions needed for build-docker-image
contents: read
Expand Down Expand Up @@ -274,11 +258,7 @@ jobs:
# Job 4: Build minimal onnxruntime [exceptions ENABLED, type reduction ENABLED (globally allowed types)] and run tests
build_minimal_globally_allowed_types:
name: 4. Build Minimal (Globally Allowed Types)
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_minimal_globally_allowed_types-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions: # Permissions needed for build-docker-image
contents: read
Expand Down Expand Up @@ -330,11 +310,7 @@ jobs:
# Job 5: Build extended minimal onnxruntime and run tests
build_extended_minimal:
name: 5. Build Extended Minimal
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_extended_minimal-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions: # Permissions needed for build-docker-image
contents: read
Expand Down Expand Up @@ -417,11 +393,7 @@ jobs:
# Job 6a: Regular build with python and all optional features disabled.
build_regular_no_optional:
name: 6a. Build Regular (No Optional Features)
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_regular_no_optional-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions: # Permissions needed for build-docker-image
contents: read
Expand Down Expand Up @@ -515,11 +487,7 @@ jobs:
# Job 6b: Minimal build with all optional features disabled.
build_minimal_no_optional:
name: 6b. Build Minimal (No Optional Features)
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_minimal_no_optional-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions: # Permissions needed for build-docker-image
contents: read
Expand Down Expand Up @@ -602,11 +570,7 @@ jobs:
# Job 6c: Extended minimal build with all optional features disabled.
build_extended_minimal_no_optional:
name: 6c. Build Extended Minimal (No Optional Features)
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_extended_minimal_no_optional-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions: # Permissions needed for build-docker-image
contents: read
Expand Down Expand Up @@ -697,11 +661,7 @@ jobs:
build_extended_minimal_android:
name: 7. Build Extended Minimal (Android NNAPI)
needs: build_full_ort # Depends on Job 1 for test data
runs-on: [
"self-hosted",
"1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU",
"JobId=build_extended_minimal_android-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}"
]
runs-on: [ort-github-linux-16-amd-wcus-ss]
timeout-minutes: 120
permissions: # Permissions needed for build-docker-image
contents: read
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/linux_openvino_ci.yml
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ jobs:
# Use the reusable workflow as the other Linux CI pipelines
uses: ./.github/workflows/reusable_linux_build.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU"
pool_name: "ort-github-linux-16-amd-wcus-ss"
build_config: Release
# Architecture: OpenVino only supports Intel X64
architecture: x64
Expand Down
Loading
Loading