Skip to content

GitLab

Unverified Commit 0f04a5f4 authored by Qi Yuhang's avatar Qi Yuhang Committed by GitHub
Browse files

Optimize cutlass int8 gemm kernel for large M on SM89 Ada GPU (#10714)

parent 2f18602f
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
sgl-kernel/csrc/gemm/int8_gemm_kernel.cu
View file @ 0f04a5f4
...@@ -409,8 +409,8 @@ void sm89_dispatch_shape( ...@@ -409,8 +409,8 @@ void sm89_dispatch_shape(
cutlass_int8_scaled_mm< cutlass_int8_scaled_mm<
ElementOutput, ElementOutput,
ArchTag, ArchTag,
cutlass::gemm::GemmShape<32, 64, 128>, cutlass::gemm::GemmShape<128, 128, 64>,
cutlass::gemm::GemmShape<16, 64, 64>, cutlass::gemm::GemmShape<64, 64, 64>,
InstructionShape, InstructionShape,
5>(out, mat_a, mat_b, scales_a, scales_b, bias); 5>(out, mat_a, mat_b, scales_a, scales_b, bias);
} }
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment