[Diffusion] [NPU] Wan2.2-T2V-A14B-Diffusers modelslim quantization support (#17996)

Co-authored-by: ronnie_zheng <zl19940307@163.com>
This commit is contained in:
Артем Савкин
2026-03-07 17:26:44 +03:00
committed by GitHub
parent f8d4eb7022
commit 5297b02c88
19 changed files with 808 additions and 166 deletions

View File

@@ -64,6 +64,7 @@ jobs:
- ".github/workflows/pr-test-npu.yml"
multimodal_gen:
- "python/sglang/multimodal_gen/**"
- "python/sglang/srt/**"
- "python/pyproject_npu.toml"
- "scripts/ci/npu/npu_ci_install_dependency.sh"
- ".github/workflows/pr-test-npu.yml"
@@ -338,3 +339,41 @@ jobs:
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
cd python
python3 sglang/multimodal_gen/test/run_suite.py --suite 2-npu
multimodal-gen-test-8-npu-a3:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.multimodal_gen == 'true'
runs-on: linux-aarch64-a3-16
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple"
pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
- name: Run test
timeout-minutes: 60
env:
SGLANG_USE_MODELSCOPE: true
SGLANG_IS_IN_CI: true
HF_ENDPOINT: https://hf-mirror.com
TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
cd python
python3 sglang/multimodal_gen/test/run_suite.py --suite 8-npu