1. 16 9月, 2021 1 次提交
  2. 09 9月, 2021 8 次提交
  3. 08 9月, 2021 3 次提交
  4. 26 8月, 2021 2 次提交
  5. 23 8月, 2021 3 次提交
  6. 18 8月, 2021 3 次提交
    • M
      Merge pull request #162 from RomeoV/master · 6456fb4a
      Matthias Fey 提交于
      Let torch determine correct cuda architecture
      6456fb4a
    • R
      add TORCH_CUDA_ARCH_LIST to building wheels · 37f758b7
      rusty1s 提交于
      37f758b7
    • R
      Let torch determine correct cuda architecture · 407f53e2
      Romeo Valentin 提交于
      See `pytorch/torch/utils/cpp_extension.cpp:CUDAExtension`:
      >   By default the extension will be compiled to run on all archs of the cards visible during the
      >   building process of the extension, plus PTX. If down the road a new card is installed the
      >   extension may need to be recompiled. If a visible card has a compute capability (CC) that's
      >   newer than the newest version for which your nvcc can build fully-compiled binaries, Pytorch
      >   will make nvcc fall back to building kernels with the newest version of PTX your nvcc does
      >   support (see below for details on PTX).
      
      >   You can override the default behavior using `TORCH_CUDA_ARCH_LIST` to explicitly specify which
      >   CCs you want the extension to support:
      
      >   TORCH_CUDA_ARCH_LIST="6.1 8.6" python build_my_extension.py
      >   TORCH_CUDA_ARCH_LIST="5.2 6.0 6.1 7.0 7.5 8.0 8.6+PTX" python build_my_extension.py
      
      >   The +PTX option causes extension kernel binaries to include PTX instructions for the specified
      >   CC. PTX is an intermediate representation that allows kernels to runtime-compile for any CC >=
      >   the specified CC (for example, 8.6+PTX generates PTX that can runtime-compile for any GPU with
      >   CC >= 8.6). This improves your binary's forward compatibility. However, relying on older PTX to
      >   provide forward compat by runtime-compiling for newer CCs can modestly reduce performance on
      >   those newer CCs. If you know exact CC(s) of the GPUs you want to target, you're always better
      >   off specifying them individually. For example, if you want your extension to run on 8.0 and 8.6,
      >   "8.0+PTX" would work functionally because it includes PTX that can runtime-compile for 8.6, but
      >   "8.0 8.6" would be better.
      
      >   Note that while it's possible to include all supported archs, the more archs get included the
      >   slower the building process will be, as it will build a separate kernel image for each arch.
      407f53e2
  7. 16 8月, 2021 1 次提交
  8. 15 8月, 2021 1 次提交
    • R
      typo · 3dbd2282
      rusty1s 提交于
      3dbd2282
  9. 10 8月, 2021 3 次提交
  10. 30 7月, 2021 2 次提交
  11. 29 7月, 2021 6 次提交
  12. 28 7月, 2021 1 次提交
  13. 22 7月, 2021 1 次提交
  14. 21 7月, 2021 3 次提交
  15. 14 7月, 2021 2 次提交