Add NPU basic function testcases (#19382)

Co-authored-by: cy <chenyang08056032@163.com>
Co-authored-by: Cherry_ming <136634645@qq.com>

.github/workflows/nightly-test-npu.yml

@@ -50,7 +50,6 @@ jobs:
           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
@@ -71,7 +70,18 @@ jobs:
           PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
           STREAMS_PER_DEVICE: 32
         run: |
-          pip install sentence_transformers accelerate
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
           cd test
           python3 run_suite.py --hw npu --suite nightly-1-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
 
@@ -98,7 +108,6 @@ jobs:
           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
@@ -118,7 +127,18 @@ jobs:
           PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
           STREAMS_PER_DEVICE: 32
         run: |
-          pip install sentence_transformers accelerate
+          pip install sglang_router
+          hf download lmms-lab/MMMU --repo-type dataset
+          pip install sentence_transformers torchaudio==2.8.0
+          pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
+          git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
+          cd ./lmms-eval
+          nohup pip install . > lmmslog.txt 2>&1 &
+          sleep 120
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          cd ../
           cd test
           python3 run_suite.py --hw npu --suite nightly-2-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 1
 
@@ -142,9 +162,8 @@ jobs:
           # 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.trusted-host "${CACHING_URL}"
-
+          pip config set global.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple"
+          pip config set global.trusted-host "${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
@@ -165,10 +184,11 @@ jobs:
           PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
           STREAMS_PER_DEVICE: 32
         run: |
+          pip install sglang_router
           hf download lmms-lab/MMMU --repo-type dataset
-          pip install sentence_transformers
+          pip install sentence_transformers torchaudio==2.8.0
           pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
-          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter peft==0.2.0 black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
           pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
           git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
           cd ./lmms-eval
@@ -202,7 +222,6 @@ jobs:
           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
@@ -223,10 +242,11 @@ jobs:
           PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
           STREAMS_PER_DEVICE: 32
         run: |
+          pip install sglang_router
           hf download lmms-lab/MMMU --repo-type dataset
-          pip install sentence_transformers
+          pip install sentence_transformers torchaudio==2.8.0
           pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
-          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter peft==0.2.0 black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
           pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
           git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
           cd ./lmms-eval
@@ -243,7 +263,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        part: [0]
+        part: [0, 1]
     container:
       image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
     steps:
@@ -260,7 +280,6 @@ jobs:
           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
@@ -281,10 +300,11 @@ jobs:
           PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
           STREAMS_PER_DEVICE: 32
         run: |
+          pip install sglang_router
           hf download lmms-lab/MMMU --repo-type dataset
-          pip install sentence_transformers
+          pip install sentence_transformers torchaudio==2.8.0
           pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
-          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter peft==0.2.0 black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
+          pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
           pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
           git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
           cd ./lmms-eval
@@ -293,7 +313,7 @@ jobs:
           export PYTHONPATH=$PYTHONPATH:$(pwd)
           cd ../
           cd test
-          python3 run_suite.py --hw npu --suite nightly-16-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 1
+          python3 run_suite.py --hw npu --suite nightly-16-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
 
   check-all-jobs:
     if: github.repository == 'sgl-project/sglang' && always()