We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent c3d9883 commit 24b17d8Copy full SHA for 24b17d8
csrc/setup_cuda.py
@@ -226,6 +226,7 @@ def get_gencode_flags():
226
"gpu/fp8_gemm_with_cutlass/fp8_fp8_half_block_gemm.cu",
227
"gpu/fp8_gemm_with_cutlass/fp8_fp8_half_gemm_ptr_scale.cu",
228
]
229
+ sources += find_end_files("./gpu/mla_attn", ".cu")
230
sources += [
231
"gpu/sparse/sparse_compressor.cu",
232
"gpu/sparse/sparse_mm.cu",
0 commit comments