|
|
|
|
|
|
by pjmlp
51 days ago
|
|
|
To note that enough people have tried to do things in Python, that now writing CUDA kernels in Python is also a supported way, still WIP but NVidia is quite serious about it. Basically their GPU JIT builds on top of MLIR, thus in the end is no different from anything else on top of LLVM. |
|
|