OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-06 12:20:52 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity

[CI] Move CUDA tests to trunk workflow (#160379)

Browse Source 
Which is getting run before PR is merged anyway, but according to 3X
less frequently than pull workflow according to [Flambeau](https://pytorchci.grafana.net/public-dashboards/1c571e79090443eaaa9811db71f8d23b)
<img width="796" height="573" alt="image" src="https://github.com/user-attachments/assets/0235e610-4e1c-4be5-88bf-ea8278d1c656" />

I.e. that will probably results in some longer time to signal, but considering that frequency of changes to eager PyTorch-on-CUDA slowed down and Inductor changes are decorated with ciflow/inductor, this looks like an acceptable tradeoff to reduce costs
Pull Request resolved: https://github.com/pytorch/pytorch/pull/160379
Approved by: https://github.com/izaitsevfb
This commit is contained in:
Nikita Shulga 2025-08-11 16:25:13 -07:00 committed by PyTorch MergeBot
parent 10bc36fe84
commit edaa151d0d
2 changed files with 37 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
.github/workflows/pull.yml vendored
View File

@ -254,42 +254,6 @@ jobs:
timeout-minutes: 600
secrets: inherit
linux-jammy-cuda12_8-py3_10-gcc11-build:
name: linux-jammy-cuda12.8-py3.10-gcc11
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
build-environment: linux-jammy-cuda12.8-py3.10-gcc11
docker-image-name: ci-image:pytorch-linux-jammy-cuda12.8-cudnn9-py3-gcc11
cuda-arch-list: '7.5 8.9'
test-matrix: |
{ include: [
{ config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
{ config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
{ config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
{ config: "pr_time_benchmarks", shard: 1, num_shards: 1, runner: "linux.g4dn.metal.nvidia.gpu" },
]}
secrets: inherit
linux-jammy-cuda12_8-py3_10-gcc11-test:
name: linux-jammy-cuda12.8-py3.10-gcc11
uses: ./.github/workflows/_linux-test.yml
needs:
- linux-jammy-cuda12_8-py3_10-gcc11-build
- target-determination
with:
timeout-minutes: 360
build-environment: linux-jammy-cuda12.8-py3.10-gcc11
docker-image: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build.outputs.test-matrix }}
secrets: inherit
linux-jammy-cuda12_8-cudnn9-py3_9-clang12-build:
name: linux-jammy-cuda12.8-cudnn9-py3.9-clang12
uses: ./.github/workflows/_linux-build.yml

37
.github/workflows/trunk.yml vendored
View File

@ -63,6 +63,43 @@ jobs:
]}
secrets: inherit
linux-jammy-cuda12_8-py3_10-gcc11-build:
name: linux-jammy-cuda12.8-py3.10-gcc11
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
build-environment: linux-jammy-cuda12.8-py3.10-gcc11
docker-image-name: ci-image:pytorch-linux-jammy-cuda12.8-cudnn9-py3-gcc11
cuda-arch-list: '7.5 8.9'
test-matrix: |
{ include: [
{ config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g6.4xlarge.experimental.nvidia.gpu" },
{ config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
{ config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
{ config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu" },
{ config: "pr_time_benchmarks", shard: 1, num_shards: 1, runner: "linux.g4dn.metal.nvidia.gpu" },
]}
secrets: inherit
linux-jammy-cuda12_8-py3_10-gcc11-test:
name: linux-jammy-cuda12.8-py3.10-gcc11
uses: ./.github/workflows/_linux-test.yml
needs:
- linux-jammy-cuda12_8-py3_10-gcc11-build
- target-determination
with:
timeout-minutes: 360
build-environment: linux-jammy-cuda12.8-py3.10-gcc11
docker-image: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build.outputs.test-matrix }}
secrets: inherit
# no-ops builds test USE_PER_OPERATOR_HEADERS=0 where ATen/ops is not generated
linux-jammy-cuda12_8-py3_10-gcc11-no-ops-build:
name: linux-jammy-cuda12.8-py3.10-gcc11-no-ops