Views
No views yet
onnxruntime-gpu wheel — 目前公開可取得的第一個適用於此平台的版本。onnxruntime-gpu wheel for NVIDIA DGX Spark (GB10 Blackwell) and Jetson Thor — the first publicly available wheel for this platform.onnxruntime-gpu wheel,只提供 x86_64 版本。這個 wheel 是專門為 NVIDIA GB10 (SM121) Blackwell 架構從源碼編譯的。onnxruntime-gpu wheel for aarch64 + CUDA 13 on PyPI (x86_64 only). This wheel was compiled from source specifically for the NVIDIA GB10 (SM121) Blackwell architecture.| 項目 / Item | 值 / Value |
|---|---|
| 版本 / Version | 1.25.0 (從 main branch 編譯) |
| Python | 3.12 (cp312) |
| 平台 / Platform | linux_aarch64 |
| CUDA | 13.1 (向前相容 13.0 driver) |
| cuDNN | 9.17.1 |
| CUDA Arch | SM121 (Blackwell) |
| Providers | CUDAExecutionProvider, CPUExecutionProvider |
pip install https://huggingface.co/Jay0515/onnxruntime-gpu-aarch64-cuda13-sm121/resolve/main/onnxruntime_gpu-1.25.0-cp312-cp312-linux_aarch64.whl1pip install nvidia-cudnn-cu12
2export LD_LIBRARY_PATH=$(python -c "import nvidia.cudnn; print(nvidia.cudnn.__path__[0])")/lib:$LD_LIBRARY_PATH1import onnxruntime
2print(onnxruntime.get_available_providers())
3# 預期輸出 / Expected: ['CUDAExecutionProvider', 'CPUExecutionProvider']1git clone --recursive --depth 1 https://github.com/microsoft/onnxruntime
2cd onnxruntime
3
4export CMAKE_BUILD_PARALLEL_LEVEL=4 # 限制並行數,避免 OOM
5
6./build.sh \
7 --config Release \
8 --build_shared_lib \
9 --parallel 4 \
10 --use_cuda \
11 --cuda_home /usr/local/cuda \
12 --cudnn_home /usr \
13 --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=121 \
14 --build_wheel \
15 --skip_tests \
16 --allow_running_as_root| 配置 / Configuration | 20 段音檔 / 20 audio segments | 加速比 / Speedup |
|---|---|---|
| PyTorch (FunASR) | 40.4s | 1.0x |
| ONNX+GGUF (CPU encoder) | 9.23s | 4.4x |
| ONNX+GGUF (CUDA encoder) | 5.75s | 7.0x |