Jeff Daily 6ede882c0b preferred blas library; cublaslt gemm implementation (#122106) ... Following the example of PyTorch supporting a preferred Linalg library (cusolver or magma), this PR introduces a preferred blas library selector of either cublas or cublaslt for CUDA and hipblas or hipblaslt for ROCm via normal hipification of sources. The default blas implementation remains cublas or hipblas. cublaslt or hipblaslt can be enabled using environment variable TORCH_BLAS_PREFER_CUBLASLT=1 (or TORCH_BLAS_PREFER_HIPBLASLT=1 as an alias) or by calling `torch.backends.cuda.preferred_blas_library(backend="cublaslt")` or as an alias `backend="hipblaslt"`. Pull Request resolved: https://github.com/pytorch/pytorch/pull/122106 Approved by: https://github.com/lezcano		2024-04-22 15:38:22 +00:00
..
_internal	preferred blas library; cublaslt gemm implementation (#122106)	2024-04-22 15:38:22 +00:00
__init__.py	document torch.testing.assert_allclose (#89526)	2022-12-01 11:22:50 +00:00
_comparison.py	[BE] enable ruff rule RSE and remove useless parentheses in raise statements (#124261)	2024-04-17 19:29:34 +00:00
_creation.py	additional support for float8_e4m3fnuz and _e5m2fnuz (#115214)	2024-01-22 18:33:41 +00:00