{"author":"Francis Lam","author_email":"flam@alum.mit.edu","author_time":1711572189,"commit_time":1711572189,"committer":"GitHub","committer_email":"noreply@github.com","hash":"7c5729a3bdeab541c5d91682284d8f0b182f10f4","message":"wmma: refactor to remove wmma_func and create TC funcs as needed (#3945)\n\n* wmma: refactor to remove wmma_func and create TC funcs as needed\r\n\r\n* test_linearizer: disable bf16 CUDA during emulation testing\r\n\r\n* cstyle: clean up creation of CUDA vec dtypes\r\n\r\n* extra/gemm: add option to accumulate to bfloat16\r\n\r\n* cleanups\r\n\r\n* benchmark: add CUDA bfloat16 matmul\r\n\r\n* more cleanups","parents":["88b24df40a4f0b486e10c363bba3a45dfb298628"],"tree_hash":"c2e756a99340277c4ffe8c31c0d9beb015bc3c5f"}