[NPU] [Diffusion] Fix critical Ascend NPU Diffusion regression/bugs & restore 2-NPU CI testcase (#34855)

Co-authored-by: Elizaveta Martirosian <elizabet3000@mail.ru>
Co-authored-by: Arseniy Mironov <98156294+Napkin-AI@users.noreply.github.com>
Co-authored-by: Alexandr <117110413+Allor-maker@users.noreply.github.com>
Co-authored-by: P_Alex_Tr <aleksandr.smyshlaev@yandex.ru>
This commit is contained in:
Артем Савкин
2026-08-22 18:32:20 +03:00
committed by GitHub
co-authored by Elizaveta Martirosian Arseniy Mironov Alexandr P_Alex_Tr
parent 0b064e3739
commit b98d472158
20 changed files with 356 additions and 64 deletions
+20 -6
View File
@@ -167,6 +167,10 @@ jobs:
needs: [check-changes, pr-gate, set-image-config]
if: ${{ !failure() && !cancelled() && needs.check-changes.outputs.multimodal_gen == 'true' }}
runs-on: linux-aarch64-a3-800t-2
strategy:
fail-fast: false
matrix:
part: [0, 1]
container:
image: ${{ needs.set-image-config.outputs.CANN_image_a3 }}
steps:
@@ -209,21 +213,28 @@ jobs:
SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
run: |
cd python
python3 sglang/multimodal_gen/test/run_suite.py --suite 1-npu
python3 sglang/multimodal_gen/test/run_suite.py \
--suite 1-npu \
--partition-id ${{ matrix.part }} \
--total-partitions 2
- name: Upload diffusion failure artifacts
if: always()
uses: actions/upload-artifact@v4
with:
name: diffusion-failures-npu-1-${{ github.run_attempt }}
name: diffusion-failures-npu-1-part${{ matrix.part }}-${{ github.run_attempt }}
path: diffusion-failures/
if-no-files-found: ignore
retention-days: 7
multimodal-gen-test-2-npu-a3:
needs: [check-changes, pr-gate, set-image-config]
if: false # Temporarily disabled; will be restored once the issue is fixed.
runs-on: linux-aarch64-a3-800t-2
if: ${{ !failure() && !cancelled() && needs.check-changes.outputs.multimodal_gen == 'true' }}
runs-on: linux-aarch64-a3-800t-16
strategy:
fail-fast: false
matrix:
part: [0, 1]
container:
image: ${{ needs.set-image-config.outputs.CANN_image_a3 }}
steps:
@@ -266,13 +277,16 @@ jobs:
SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
run: |
cd python
python3 sglang/multimodal_gen/test/run_suite.py --suite 2-npu
python3 sglang/multimodal_gen/test/run_suite.py \
--suite 2-npu \
--partition-id ${{ matrix.part }} \
--total-partitions 2
- name: Upload diffusion failure artifacts
if: always()
uses: actions/upload-artifact@v4
with:
name: diffusion-failures-npu-2-${{ github.run_attempt }}
name: diffusion-failures-npu-2-part${{ matrix.part }}-${{ github.run_attempt }}
path: diffusion-failures/
if-no-files-found: ignore
retention-days: 7