* Add more GPU architectures support * Update layout.py * Optimize performance, Add SM90 support, Add 1D2D SM100 support * Add fmtlib submodule at commit 553ec11 --------- Co-authored-by: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com>
14 lines
396 B
Plaintext
14 lines
396 B
Plaintext
#include <deep_gemm/impls/sm90_bf16_gemm.cuh>
|
|
#include <deep_gemm/impls/sm100_bf16_gemm.cuh>
|
|
#include <deep_gemm/impls/sm90_fp8_gemm_1d1d.cuh>
|
|
#include <deep_gemm/impls/sm90_fp8_gemm_1d2d.cuh>
|
|
#include <deep_gemm/impls/sm100_fp8_gemm_1d1d.cuh>
|
|
#include <deep_gemm/impls/sm100_fp8_gemm_1d2d.cuh>
|
|
#include <deep_gemm/impls/smxx_layout.cuh>
|
|
|
|
using namespace deep_gemm;
|
|
|
|
int main() {
|
|
return 0;
|
|
}
|