From d33515aea7967ce20303e45e77f7b2d0bc6e0bdd Mon Sep 17 00:00:00 2001 From: "hongliang.yuan" Date: Wed, 25 Jun 2025 10:23:27 +0800 Subject: [PATCH] add lost requirements --- .../transformer_asr/ixrt/ci/prepare.sh | 2 ++ .../densenet121/ixrt/ci/prepare.sh | 2 ++ .../igie_common/requirements.txt | 1 + .../cv/classification/repvgg/igie/README.md | 2 +- .../classification/repvgg/igie/ci/prepare.sh | 2 +- .../mask_rcnn/ixrt/ci/prepare.sh | 2 +- .../centernet/igie/requirements.txt | 2 +- .../centernet/ixrt/requirements.txt | 2 +- .../foveabox/igie/requirements.txt | 2 +- .../foveabox/ixrt/requirements.txt | 2 +- .../hrnet/igie/requirements.txt | 2 +- .../hrnet/ixrt/requirements.txt | 2 +- .../paa/igie/requirements.txt | 2 +- .../retinanet/igie/requirements.txt | 2 +- .../yolov12/igie/requirements.txt | 1 + .../yolov6/igie/requirements.txt | 1 + .../yolov6/ixrt/requirements.txt | 3 +- .../yolov7/igie/requirements.txt | 1 + .../yolox/igie/requirements.txt | 1 + .../object_detection/yolox/ixrt/ci/prepare.sh | 2 +- .../yolox/ixrt/requirements.txt | 3 +- .../pose_estimation/hrnetpose/igie/README.md | 8 +++-- .../hrnetpose/igie/ci/prepare.sh | 8 +++-- .../hrnetpose/igie/requirements.txt | 1 - .../cv/pose_estimation/rtmpose/igie/README.md | 8 +++-- .../rtmpose/igie/ci/prepare.sh | 17 ++++++++-- .../rtmpose/igie/requirements.txt | 1 - .../cv/pose_estimation/rtmpose/ixrt/README.md | 8 +++-- .../rtmpose/ixrt/ci/prepare.sh | 6 +++- .../rtmpose/ixrt/requirements.txt | 1 - .../unet/igie/requirements.txt | 5 +-- .../vision_language_model/aria/vllm/README.md | 1 - .../aria/vllm/ci/prepare.sh | 3 +- models/nlp/llm/qwen1.5-14b/vllm/README.md | 2 +- .../plm/bert_base_ner/igie/requirements.txt | 1 + .../plm/bert_base_squad/ixrt/ci/prepare.sh | 2 +- .../bert_large_squad/igie/requirements.txt | 1 + .../plm/bert_large_squad/ixrt/ci/prepare.sh | 2 +- tests/run_igie.py | 12 +++++++ tests/run_ixrt.py | 33 +++++++++++++++---- tests/run_trtllm.py | 6 +++- tests/run_vllm.py | 7 ++-- 42 files changed, 125 insertions(+), 47 deletions(-) diff --git a/models/audio/speech_recognition/transformer_asr/ixrt/ci/prepare.sh b/models/audio/speech_recognition/transformer_asr/ixrt/ci/prepare.sh index 7cb003cf..2fb3ec41 100644 --- a/models/audio/speech_recognition/transformer_asr/ixrt/ci/prepare.sh +++ b/models/audio/speech_recognition/transformer_asr/ixrt/ci/prepare.sh @@ -19,8 +19,10 @@ set -x ID=$(grep -oP '(?<=^ID=).+' /etc/os-release | tr -d '"') if [[ ${ID} == "ubuntu" ]]; then apt install -y libgl1-mesa-glx + apt install sox libsox-fmt-all elif [[ ${ID} == "centos" ]]; then yum install -y mesa-libGL + yum install sox sox-devel -y else echo "Not Support Os" fi diff --git a/models/cv/classification/densenet121/ixrt/ci/prepare.sh b/models/cv/classification/densenet121/ixrt/ci/prepare.sh index 8d542a84..50a812d5 100644 --- a/models/cv/classification/densenet121/ixrt/ci/prepare.sh +++ b/models/cv/classification/densenet121/ixrt/ci/prepare.sh @@ -27,4 +27,6 @@ fi pip install -r ../../ixrt_common/requirements.txt mkdir checkpoints +mkdir -p /root/.cache/torch/hub/checkpoints/ +cp /root/data/checkpoints/densenet121-a639ec97.pth /root/.cache/torch/hub/checkpoints/ python3 export.py --output checkpoints/densenet121.onnx \ No newline at end of file diff --git a/models/cv/classification/igie_common/requirements.txt b/models/cv/classification/igie_common/requirements.txt index 9e811126..7096be1e 100644 --- a/models/cv/classification/igie_common/requirements.txt +++ b/models/cv/classification/igie_common/requirements.txt @@ -1,2 +1,3 @@ onnx tqdm +onnxsim \ No newline at end of file diff --git a/models/cv/classification/repvgg/igie/README.md b/models/cv/classification/repvgg/igie/README.md index 4a3c87d5..6ee9e4f4 100644 --- a/models/cv/classification/repvgg/igie/README.md +++ b/models/cv/classification/repvgg/igie/README.md @@ -28,7 +28,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx pip3 install -r ../../igie_common/requirements.txt -pip3 install mmcv==1.5.3 mmcls==0.24.0 +pip3 install mmcv==1.5.3 mmcls==0.24.0 mmengine ``` ### Model Conversion diff --git a/models/cv/classification/repvgg/igie/ci/prepare.sh b/models/cv/classification/repvgg/igie/ci/prepare.sh index 2daf189b..7665a75d 100644 --- a/models/cv/classification/repvgg/igie/ci/prepare.sh +++ b/models/cv/classification/repvgg/igie/ci/prepare.sh @@ -25,6 +25,6 @@ else echo "Not Support Os" fi pip3 install -r ../../igie_common/requirements.txt -pip3 install mmcv==1.5.3 mmcls==0.24.0 +pip3 install mmcv==1.5.3 mmcls==0.24.0 mmengine unzip -q /mnt/deepspark/data/repos/mmpretrain-0.24.0.zip -d ./ python3 ../../igie_common/export_mmcls.py --cfg mmpretrain/configs/repvgg/repvgg-A0_4xb64-coslr-120e_in1k.py --weight repvgg-A0_8xb32_in1k_20221213-60ae8e23.pth --output repvgg.onnx \ No newline at end of file diff --git a/models/cv/instance_segmentation/mask_rcnn/ixrt/ci/prepare.sh b/models/cv/instance_segmentation/mask_rcnn/ixrt/ci/prepare.sh index 022d4d31..34e7de53 100644 --- a/models/cv/instance_segmentation/mask_rcnn/ixrt/ci/prepare.sh +++ b/models/cv/instance_segmentation/mask_rcnn/ixrt/ci/prepare.sh @@ -19,7 +19,7 @@ set -x ln -s /root/data/checkpoints/maskrcnn.wts ./python/ ln -s /root/data/datasets/coco ./coco # install ixrt run -bash /root/data/3rd_party/ixrt-0.10.0+corex.4.2.0.20250115-linux_x86_64.run +bash /root/data/install/ixrt-1.0.0.alpha+corex.4.3.0-linux_x86_64.run if [ "$1" = "nvidia" ]; then cd scripts && bash init_nv.sh diff --git a/models/cv/object_detection/centernet/igie/requirements.txt b/models/cv/object_detection/centernet/igie/requirements.txt index 71ef3c22..78604037 100644 --- a/models/cv/object_detection/centernet/igie/requirements.txt +++ b/models/cv/object_detection/centernet/igie/requirements.txt @@ -1,5 +1,5 @@ onnx tqdm mmdet -mmdeploy +mmdeploy==1.3.1 mmengine diff --git a/models/cv/object_detection/centernet/ixrt/requirements.txt b/models/cv/object_detection/centernet/ixrt/requirements.txt index 291a7172..85763e9d 100644 --- a/models/cv/object_detection/centernet/ixrt/requirements.txt +++ b/models/cv/object_detection/centernet/ixrt/requirements.txt @@ -1,6 +1,6 @@ onnx tqdm mmdet -mmdeploy +mmdeploy==1.3.1 mmengine transformers==4.37.1 \ No newline at end of file diff --git a/models/cv/object_detection/foveabox/igie/requirements.txt b/models/cv/object_detection/foveabox/igie/requirements.txt index 073c19fb..520dadd4 100644 --- a/models/cv/object_detection/foveabox/igie/requirements.txt +++ b/models/cv/object_detection/foveabox/igie/requirements.txt @@ -2,5 +2,5 @@ onnx tqdm onnxsim mmdet -mmdeploy +mmdeploy==1.3.1 mmengine diff --git a/models/cv/object_detection/foveabox/ixrt/requirements.txt b/models/cv/object_detection/foveabox/ixrt/requirements.txt index 6b25e9d9..4931fc16 100644 --- a/models/cv/object_detection/foveabox/ixrt/requirements.txt +++ b/models/cv/object_detection/foveabox/ixrt/requirements.txt @@ -3,6 +3,6 @@ onnx onnxsim ultralytics pycocotools -mmdeploy +mmdeploy==1.3.1 mmdet opencv-python==4.6.0.66 \ No newline at end of file diff --git a/models/cv/object_detection/hrnet/igie/requirements.txt b/models/cv/object_detection/hrnet/igie/requirements.txt index 073c19fb..520dadd4 100644 --- a/models/cv/object_detection/hrnet/igie/requirements.txt +++ b/models/cv/object_detection/hrnet/igie/requirements.txt @@ -2,5 +2,5 @@ onnx tqdm onnxsim mmdet -mmdeploy +mmdeploy==1.3.1 mmengine diff --git a/models/cv/object_detection/hrnet/ixrt/requirements.txt b/models/cv/object_detection/hrnet/ixrt/requirements.txt index 073c19fb..520dadd4 100644 --- a/models/cv/object_detection/hrnet/ixrt/requirements.txt +++ b/models/cv/object_detection/hrnet/ixrt/requirements.txt @@ -2,5 +2,5 @@ onnx tqdm onnxsim mmdet -mmdeploy +mmdeploy==1.3.1 mmengine diff --git a/models/cv/object_detection/paa/igie/requirements.txt b/models/cv/object_detection/paa/igie/requirements.txt index 073c19fb..520dadd4 100644 --- a/models/cv/object_detection/paa/igie/requirements.txt +++ b/models/cv/object_detection/paa/igie/requirements.txt @@ -2,5 +2,5 @@ onnx tqdm onnxsim mmdet -mmdeploy +mmdeploy==1.3.1 mmengine diff --git a/models/cv/object_detection/retinanet/igie/requirements.txt b/models/cv/object_detection/retinanet/igie/requirements.txt index 073c19fb..520dadd4 100644 --- a/models/cv/object_detection/retinanet/igie/requirements.txt +++ b/models/cv/object_detection/retinanet/igie/requirements.txt @@ -2,5 +2,5 @@ onnx tqdm onnxsim mmdet -mmdeploy +mmdeploy==1.3.1 mmengine diff --git a/models/cv/object_detection/yolov12/igie/requirements.txt b/models/cv/object_detection/yolov12/igie/requirements.txt index ba0fdc99..355ab489 100644 --- a/models/cv/object_detection/yolov12/igie/requirements.txt +++ b/models/cv/object_detection/yolov12/igie/requirements.txt @@ -1,2 +1,3 @@ tqdm onnx==1.13.0 +huggingface_hub \ No newline at end of file diff --git a/models/cv/object_detection/yolov6/igie/requirements.txt b/models/cv/object_detection/yolov6/igie/requirements.txt index 238c13c6..9a992b72 100644 --- a/models/cv/object_detection/yolov6/igie/requirements.txt +++ b/models/cv/object_detection/yolov6/igie/requirements.txt @@ -2,3 +2,4 @@ tqdm onnx onnxsim pycocotools +requests \ No newline at end of file diff --git a/models/cv/object_detection/yolov6/ixrt/requirements.txt b/models/cv/object_detection/yolov6/ixrt/requirements.txt index dc83ddaf..10e819b6 100644 --- a/models/cv/object_detection/yolov6/ixrt/requirements.txt +++ b/models/cv/object_detection/yolov6/ixrt/requirements.txt @@ -3,4 +3,5 @@ onnx onnxsim pycocotools pycuda -numpy==1.24.0 \ No newline at end of file +numpy==1.24.0 +requests \ No newline at end of file diff --git a/models/cv/object_detection/yolov7/igie/requirements.txt b/models/cv/object_detection/yolov7/igie/requirements.txt index ba3dfe46..20137ef4 100644 --- a/models/cv/object_detection/yolov7/igie/requirements.txt +++ b/models/cv/object_detection/yolov7/igie/requirements.txt @@ -3,3 +3,4 @@ onnx onnxsim pycocotools seaborn +requests \ No newline at end of file diff --git a/models/cv/object_detection/yolox/igie/requirements.txt b/models/cv/object_detection/yolox/igie/requirements.txt index 238c13c6..f88d8c99 100644 --- a/models/cv/object_detection/yolox/igie/requirements.txt +++ b/models/cv/object_detection/yolox/igie/requirements.txt @@ -2,3 +2,4 @@ tqdm onnx onnxsim pycocotools +ninja==1.11.1.3 \ No newline at end of file diff --git a/models/cv/object_detection/yolox/ixrt/ci/prepare.sh b/models/cv/object_detection/yolox/ixrt/ci/prepare.sh index 6e5a49ed..fb99838a 100644 --- a/models/cv/object_detection/yolox/ixrt/ci/prepare.sh +++ b/models/cv/object_detection/yolox/ixrt/ci/prepare.sh @@ -29,7 +29,7 @@ pip install -r requirements.txt unzip -q /root/data/repos/yolox-f00a798c8bf59f43ab557a2f3d566afa831c8887.zip -d ./ ln -s /root/data/checkpoints/yolox_m.pth ./YOLOX/ # install ixrt run -bash /root/data/3rd_party/ixrt-0.10.0+corex.4.2.0.20250115-linux_x86_64.run +bash /root/data/install/ixrt-1.0.0.alpha+corex.4.3.0-linux_x86_64.run cd YOLOX && python3 setup.py develop && python3 tools/export_onnx.py --output-name ../yolox.onnx -n yolox-m -c yolox_m.pth --batch-size 32 if [ "$1" = "nvidia" ]; then cd ../plugin && mkdir -p build && cd build && cmake .. -DUSE_TRT=1 && make -j12 diff --git a/models/cv/object_detection/yolox/ixrt/requirements.txt b/models/cv/object_detection/yolox/ixrt/requirements.txt index 942d452b..a64772f7 100644 --- a/models/cv/object_detection/yolox/ixrt/requirements.txt +++ b/models/cv/object_detection/yolox/ixrt/requirements.txt @@ -6,4 +6,5 @@ pycocotools ppq pycuda protobuf==3.20.0 -opencv-python==4.6.0.66 \ No newline at end of file +opencv-python==4.6.0.66 +ninja==1.11.1.3 \ No newline at end of file diff --git a/models/cv/pose_estimation/hrnetpose/igie/README.md b/models/cv/pose_estimation/hrnetpose/igie/README.md index 39a574e5..7af12fba 100644 --- a/models/cv/pose_estimation/hrnetpose/igie/README.md +++ b/models/cv/pose_estimation/hrnetpose/igie/README.md @@ -30,8 +30,12 @@ wget https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_coco_256x192 yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx - -pip3 install -r requirements.txt +# before install mmpose==1.3.1 need to install chchumpy==0.70 which is too older that is not compatible with newer Python versions or pip +# so need to downgrade pip to version 20.2.4 +pip install pip==20.2.4 +pip install mmpose==1.3.1 +pip install --upgrade pip +pip install -r requirements.txt ``` ### Model Conversion diff --git a/models/cv/pose_estimation/hrnetpose/igie/ci/prepare.sh b/models/cv/pose_estimation/hrnetpose/igie/ci/prepare.sh index 67d2d51e..6135d20f 100644 --- a/models/cv/pose_estimation/hrnetpose/igie/ci/prepare.sh +++ b/models/cv/pose_estimation/hrnetpose/igie/ci/prepare.sh @@ -24,8 +24,12 @@ elif [[ ${ID} == "centos" ]]; then else echo "Not Support Os" fi - -pip3 install -r requirements.txt +# before install mmpose==1.3.1 need to install chchumpy==0.70 which is too older that is not compatible with newer Python versions or pip +# so need to downgrade pip to version 20.2.4 +pip install pip==20.2.4 +pip install mmpose==1.3.1 +pip install --upgrade pip +pip install -r requirements.txt # export onnx model python3 export.py --weight hrnet_w32_coco_256x192-c78dce93_20200708.pth --cfg td-hm_hrnet-w32_8xb64-210e_coco-256x192.py --input 1,3,256,192 --output hrnetpose.onnx diff --git a/models/cv/pose_estimation/hrnetpose/igie/requirements.txt b/models/cv/pose_estimation/hrnetpose/igie/requirements.txt index f0819936..b6b3fff4 100644 --- a/models/cv/pose_estimation/hrnetpose/igie/requirements.txt +++ b/models/cv/pose_estimation/hrnetpose/igie/requirements.txt @@ -2,6 +2,5 @@ onnx tqdm onnxsim mmdet==3.3.0 -mmpose==1.3.1 mmdeploy==1.3.1 mmengine==0.10.4 diff --git a/models/cv/pose_estimation/rtmpose/igie/README.md b/models/cv/pose_estimation/rtmpose/igie/README.md index b3d0ac19..a615bd46 100644 --- a/models/cv/pose_estimation/rtmpose/igie/README.md +++ b/models/cv/pose_estimation/rtmpose/igie/README.md @@ -30,8 +30,12 @@ wget https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx - -pip3 install -r requirements.txt +# before install mmpose==1.3.1 need to install chchumpy==0.70 which is too older that is not compatible with newer Python versions or pip +# so need to downgrade pip to version 20.2.4 +pip install pip==20.2.4 +pip install mmpose==1.3.1 +pip install --upgrade pip +pip install -r requirements.txt ``` ### Model Conversion diff --git a/models/cv/pose_estimation/rtmpose/igie/ci/prepare.sh b/models/cv/pose_estimation/rtmpose/igie/ci/prepare.sh index 5db28135..3c74c147 100644 --- a/models/cv/pose_estimation/rtmpose/igie/ci/prepare.sh +++ b/models/cv/pose_estimation/rtmpose/igie/ci/prepare.sh @@ -16,9 +16,20 @@ set -x -apt install -y libgl1-mesa-glx - -pip3 install -r requirements.txt +ID=$(grep -oP '(?<=^ID=).+' /etc/os-release | tr -d '"') +if [[ ${ID} == "ubuntu" ]]; then + apt install -y libgl1-mesa-glx +elif [[ ${ID} == "centos" ]]; then + yum install -y mesa-libGL +else + echo "Not Support Os" +fi +# before install mmpose==1.3.1 need to install chchumpy==0.70 which is too older that is not compatible with newer Python versions or pip +# so need to downgrade pip to version 20.2.4 +pip install pip==20.2.4 +pip install mmpose==1.3.1 +pip install --upgrade pip +pip install -r requirements.txt # export onnx model python3 export.py --weight rtmpose-m_simcc-aic-coco_pt-aic-coco_420e-256x192-63eb25f7_20230126.pth --cfg rtmpose-m_8xb256-420e_coco-256x192.py --output rtmpose.onnx diff --git a/models/cv/pose_estimation/rtmpose/igie/requirements.txt b/models/cv/pose_estimation/rtmpose/igie/requirements.txt index f0819936..b6b3fff4 100644 --- a/models/cv/pose_estimation/rtmpose/igie/requirements.txt +++ b/models/cv/pose_estimation/rtmpose/igie/requirements.txt @@ -2,6 +2,5 @@ onnx tqdm onnxsim mmdet==3.3.0 -mmpose==1.3.1 mmdeploy==1.3.1 mmengine==0.10.4 diff --git a/models/cv/pose_estimation/rtmpose/ixrt/README.md b/models/cv/pose_estimation/rtmpose/ixrt/README.md index ad416b04..cdd76938 100644 --- a/models/cv/pose_estimation/rtmpose/ixrt/README.md +++ b/models/cv/pose_estimation/rtmpose/ixrt/README.md @@ -26,8 +26,12 @@ Dataset: to download the valida yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx - -pip3 install -r requirements.txt +# before install mmpose==1.3.1 need to install chchumpy==0.70 which is too older that is not compatible with newer Python versions or pip +# so need to downgrade pip to version 20.2.4 +pip install pip==20.2.4 +pip install mmpose==1.3.1 +pip install --upgrade pip +pip install -r requirements.txt ``` ## Model Conversion diff --git a/models/cv/pose_estimation/rtmpose/ixrt/ci/prepare.sh b/models/cv/pose_estimation/rtmpose/ixrt/ci/prepare.sh index d2af8179..cfe4f753 100644 --- a/models/cv/pose_estimation/rtmpose/ixrt/ci/prepare.sh +++ b/models/cv/pose_estimation/rtmpose/ixrt/ci/prepare.sh @@ -24,7 +24,11 @@ elif [[ ${ID} == "centos" ]]; then else echo "Not Support Os" fi - +# before install mmpose==1.3.1 need to install chchumpy==0.70 which is too older that is not compatible with newer Python versions or pip +# so need to downgrade pip to version 20.2.4 +pip install pip==20.2.4 +pip install mmpose==1.3.1 +pip install --upgrade pip pip install -r requirements.txt mkdir -p data/rtmpose diff --git a/models/cv/pose_estimation/rtmpose/ixrt/requirements.txt b/models/cv/pose_estimation/rtmpose/ixrt/requirements.txt index c7459a7a..77714c99 100644 --- a/models/cv/pose_estimation/rtmpose/ixrt/requirements.txt +++ b/models/cv/pose_estimation/rtmpose/ixrt/requirements.txt @@ -2,6 +2,5 @@ onnx tqdm onnxsim mmdet==3.3.0 -mmpose==1.3.1 mmdeploy==1.3.1 mmengine==0.10.4 \ No newline at end of file diff --git a/models/cv/semantic_segmentation/unet/igie/requirements.txt b/models/cv/semantic_segmentation/unet/igie/requirements.txt index 3f7e885b..318afa5b 100644 --- a/models/cv/semantic_segmentation/unet/igie/requirements.txt +++ b/models/cv/semantic_segmentation/unet/igie/requirements.txt @@ -3,5 +3,6 @@ tqdm onnxsim mmsegmentation==1.2.2 mmengine==0.10.7 -mmdeploy -ftfy \ No newline at end of file +mmdeploy==1.3.1 +ftfy +regex \ No newline at end of file diff --git a/models/multimodal/vision_language_model/aria/vllm/README.md b/models/multimodal/vision_language_model/aria/vllm/README.md index 7ef43e54..94cdb57d 100644 --- a/models/multimodal/vision_language_model/aria/vllm/README.md +++ b/models/multimodal/vision_language_model/aria/vllm/README.md @@ -38,7 +38,6 @@ yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx -pip install transformer==4.48.0 ``` ## Model Inference diff --git a/models/multimodal/vision_language_model/aria/vllm/ci/prepare.sh b/models/multimodal/vision_language_model/aria/vllm/ci/prepare.sh index ff5f4e53..003a1508 100644 --- a/models/multimodal/vision_language_model/aria/vllm/ci/prepare.sh +++ b/models/multimodal/vision_language_model/aria/vllm/ci/prepare.sh @@ -24,5 +24,4 @@ else echo "Not Support Os" fi -cp -r ../../vllm_public_assets/ ./ -pip install transformer==4.48.0 \ No newline at end of file +cp -r ../../vllm_public_assets/ ./ \ No newline at end of file diff --git a/models/nlp/llm/qwen1.5-14b/vllm/README.md b/models/nlp/llm/qwen1.5-14b/vllm/README.md index af13752a..5a520db3 100644 --- a/models/nlp/llm/qwen1.5-14b/vllm/README.md +++ b/models/nlp/llm/qwen1.5-14b/vllm/README.md @@ -39,7 +39,7 @@ apt install -y libgl1-mesa-glx ## Model Inference ```bash -python3 offline_inference.py --model ./data/qwen1.5/Qwen1.5-14B --max-tokens 256 -tp 1 --temperature 0.0 --max-model-len 896 +python3 offline_inference.py --model ./data/qwen1.5/Qwen1.5-14B --max-tokens 256 -tp 2 --temperature 0.0 --max-model-len 896 ``` ## Model Results diff --git a/models/nlp/plm/bert_base_ner/igie/requirements.txt b/models/nlp/plm/bert_base_ner/igie/requirements.txt index eb25b6a0..46ec1311 100644 --- a/models/nlp/plm/bert_base_ner/igie/requirements.txt +++ b/models/nlp/plm/bert_base_ner/igie/requirements.txt @@ -3,3 +3,4 @@ tqdm transformers bert4torch numpy==1.23.5 +h5py \ No newline at end of file diff --git a/models/nlp/plm/bert_base_squad/ixrt/ci/prepare.sh b/models/nlp/plm/bert_base_squad/ixrt/ci/prepare.sh index e1d8b7f3..0b82d655 100644 --- a/models/nlp/plm/bert_base_squad/ixrt/ci/prepare.sh +++ b/models/nlp/plm/bert_base_squad/ixrt/ci/prepare.sh @@ -28,7 +28,7 @@ fi pip install -r requirements.txt # install ixrt run -bash /root/data/3rd_party/ixrt-0.10.0+corex.4.2.0.20250115-linux_x86_64.run +bash /root/data/install/ixrt-1.0.0.alpha+corex.4.3.0-linux_x86_64.run if [ "$1" = "nvidia" ]; then cmake -S . -B build -DUSE_TENSORRT=true diff --git a/models/nlp/plm/bert_large_squad/igie/requirements.txt b/models/nlp/plm/bert_large_squad/igie/requirements.txt index 7543264e..1880c38a 100644 --- a/models/nlp/plm/bert_large_squad/igie/requirements.txt +++ b/models/nlp/plm/bert_large_squad/igie/requirements.txt @@ -2,3 +2,4 @@ onnx tqdm numpy==1.23.5 transformers==4.37.1 +h5py \ No newline at end of file diff --git a/models/nlp/plm/bert_large_squad/ixrt/ci/prepare.sh b/models/nlp/plm/bert_large_squad/ixrt/ci/prepare.sh index 979f9050..ebc8effc 100644 --- a/models/nlp/plm/bert_large_squad/ixrt/ci/prepare.sh +++ b/models/nlp/plm/bert_large_squad/ixrt/ci/prepare.sh @@ -26,7 +26,7 @@ else fi # install ixrt run -bash /root/data/3rd_party/ixrt-0.10.0+corex.4.2.0.20250115-linux_x86_64.run +bash /root/data/install/ixrt-1.0.0.alpha+corex.4.3.0-linux_x86_64.run if [ "$1" = "nvidia" ]; then cmake -S . -B build -DUSE_TENSORRT=true diff --git a/tests/run_igie.py b/tests/run_igie.py index ebd94e46..a8d5bf8b 100644 --- a/tests/run_igie.py +++ b/tests/run_igie.py @@ -156,6 +156,12 @@ def run_clf_testcase(model): prepare_script = f""" cd ../{model['model_path']} ln -s /mnt/deepspark/data/checkpoints/{checkpoint_n} ./ + """ + if model["category"] == "cv/semantic_segmentation": + prepare_script += """ + pip install /mnt/deepspark/install/mmcv-2.1.0+corex.4.3.0-cp310-cp310-linux_x86_64.whl + """ + prepare_script += f""" bash ci/prepare.sh ls -l | grep onnx """ @@ -231,6 +237,10 @@ def run_detec_testcase(model): ln -s /mnt/deepspark/data/checkpoints/{checkpoint_n} ./ ln -s /mnt/deepspark/data/datasets/{dataset_n} ./ """ + # for 4.3.0 sdk need pre install mmcv + prepare_script += """ + pip install /mnt/deepspark/install/mmcv-2.1.0+corex.4.3.0-cp310-cp310-linux_x86_64.whl + """ # if model["need_third_part"] and model["3rd_party_repo"]: # third_party_repo = model["3rd_party_repo"] @@ -296,10 +306,12 @@ def run_ocr_testcase(model): d_url = model["download_url"] checkpoint_n = d_url.split("/")[-1] dataset_n = model["datasets"].split("/")[-1] + # for 4.3.0 sdk need pre install paddle prepare_script = f""" cd ../{model['model_path']} ln -s /mnt/deepspark/data/checkpoints/{checkpoint_n} ./ ln -s /mnt/deepspark/data/datasets/{dataset_n} ./ + pip install /mnt/deepspark/install/paddlepaddle-3.0.0+corex.4.3.0-cp310-cp310-linux_x86_64.whl unzip -q /mnt/deepspark/data/3rd_party/PaddleOCR-release-2.6.zip -d ./PaddleOCR bash ci/prepare.sh """ diff --git a/tests/run_ixrt.py b/tests/run_ixrt.py index e00b41c0..0bf60dbc 100644 --- a/tests/run_ixrt.py +++ b/tests/run_ixrt.py @@ -146,6 +146,12 @@ def run_clf_testcase(model): prepare_script = f""" cd ../{model['model_path']} ln -s /root/data/checkpoints/{checkpoint_n} ./ + """ + if model_name == "swin_transformer_large": + prepare_script += """ + pip install /root/data/install/tensorflow-2.16.2+corex.4.3.0-cp310-cp310-linux_x86_64.whl + """ + prepare_script += """ bash ci/prepare.sh """ # add pip list info when in debug mode @@ -161,7 +167,7 @@ def run_clf_testcase(model): "FPS": r"FPS\s*:\s*(\d+\.?\d*)", "Acc1": r"Acc@1\s*:\s*(\d+\.?\d*)", "Acc5": r"Acc@5\s*:\s*(\d+\.?\d*)", - "E2E": r"E2E time\s*:\s*(\d+\.\d+)" + # "E2E": r"E2E time\s*:\s*(\d+\.\d+)" } combined_pattern = re.compile("|".join(f"(?P<{name}>{pattern})" for name, pattern in patterns.items())) @@ -241,6 +247,7 @@ def run_detec_testcase(model): cd ../{model['model_path']} ln -s /root/data/checkpoints/{checkpoint_n} ./ ln -s /root/data/datasets/{dataset_n} ./ + pip install /root/data/install/mmcv-2.1.0+corex.4.3.0-cp310-cp310-linux_x86_64.whl bash ci/prepare.sh """ @@ -381,11 +388,24 @@ def run_nlp_testcase(model): "name": model_name, "result": {}, } - prepare_script = f""" - set -x - cd ../{model['model_path']} - bash ci/prepare.sh - """ + if model_name == "roberta" or model_name == "deberta" or model_name == "albert" or model_name == "roformer" or model_name == "videobert" or model_name == "wide_and_deep": + prepare_script = f""" + set -x + cd ../{model['model_path']} + pip install /root/data/install/tensorflow-2.16.2+corex.4.3.0-cp310-cp310-linux_x86_64.whl + pip install /root/data/install/ixrt-1.0.0a0+corex.4.3.0-cp310-cp310-linux_x86_64.whl + pip install /root/data/install/cuda_python-11.8.0+corex.4.3.0-cp310-cp310-linux_x86_64.whl + bash /root/data/install/ixrt-1.0.0.alpha+corex.4.3.0-linux_x86_64.run + bash ci/prepare.sh + """ + else: + prepare_script = f""" + set -x + cd ../{model['model_path']} + pip install /root/data/install/ixrt-1.0.0a0+corex.4.3.0-cp310-cp310-linux_x86_64.whl + pip install /root/data/install/cuda_python-11.8.0+corex.4.3.0-cp310-cp310-linux_x86_64.whl + bash ci/prepare.sh + """ # add pip list info when in debug mode if utils.is_debug(): @@ -532,6 +552,7 @@ def run_instance_segmentation_testcase(model): cd ../{model['model_path']} ln -s /root/data/checkpoints/{checkpoint_n} ./ ln -s /root/data/datasets/{dataset_n} ./ + pip install /root/data/install/mmcv-2.1.0+corex.4.3.0-cp310-cp310-linux_x86_64.whl bash ci/prepare.sh ls -l | grep onnx """ diff --git a/tests/run_trtllm.py b/tests/run_trtllm.py index ac79b3b9..699e0129 100644 --- a/tests/run_trtllm.py +++ b/tests/run_trtllm.py @@ -97,6 +97,10 @@ def run_nlp_testcase(model): prepare_script = f""" set -x cd ../{model['model_path']} + pip install /mnt/deepspark/install/tensorrt_llm-0.12.0+corex.4.3.0-cp310-cp310-linux_x86_64.whl + pip install /mnt/deepspark/install/ixrt-1.0.0a0+corex.4.3.0-cp310-cp310-linux_x86_64.whl + bash /mnt/deepspark/install/ixrt-1.0.0.alpha+corex.4.3.0-linux_x86_64.run + pip install /mnt/deepspark/install/cuda_python-11.8.0+corex.4.3.0-cp310-cp310-linux_x86_64.whl bash ci/prepare.sh """ @@ -140,7 +144,7 @@ def run_nlp_testcase(model): script = f""" set -x cd ../{model['model_path']} - export CUDA_VISIBLE_DEVICES=1 + bash /mnt/deepspark/install/text-generation-inference-2.1.1_x86_64.run python3 offline_inference.py --model2path ./data/Qwen1.5-7B """ diff --git a/tests/run_vllm.py b/tests/run_vllm.py index e05973fd..c6100a40 100644 --- a/tests/run_vllm.py +++ b/tests/run_vllm.py @@ -97,6 +97,7 @@ def run_nlp_testcase(model): set -x cd ../{model['model_path']} ln -s /mnt/deepspark/data/checkpoints/{checkpoint_n} ./{model_name} + pip install /mnt/deepspark/install/xformers-0.0.26.post1+corex.4.3.0-cp310-cp310-linux_x86_64.whl bash ci/prepare.sh """ @@ -167,7 +168,7 @@ def run_nlp_testcase(model): script = f""" set -x cd ../{model['model_path']} - python3 offline_inference.py --model ./qwen1.5-14b --max-tokens 256 -tp 1 --temperature 0.0 --max-model-len 896 + python3 offline_inference.py --model ./qwen1.5-14b --max-tokens 256 -tp 2 --temperature 0.0 --max-model-len 896 """ elif model_name == "qwen1.5-32b": script = f""" @@ -290,10 +291,10 @@ def run_nlp_testcase(model): result["result"][prec]["QPS"] = float(matchs.group(2)) result["result"][prec]["status"] = "PASS" else: - pattern = r"Maximum concurrency for (\d+) tokens per request: ([\d.]+)x" + pattern = r"Maximum concurrency for ([0-9,]+) tokens per request:\s*([0-9.]+)x" matchs = re.search(pattern, sout) if matchs: - result["result"][prec]["tokens"] = int(matchs.group(1)) + result["result"][prec]["tokens"] = int(matchs.group(1).replace(',', '')) result["result"][prec]["QPS"] = float(matchs.group(2)) result["result"][prec]["status"] = "PASS" -- Gitee