[Model Bash] DeepSeek R1 BF16 Min Latency QKV A GEMM (0.5% E2E Speedup) (#34758)

Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
This commit is contained in:
Robert Shaw
2026-02-18 07:42:36 -08:00
committed by GitHub
co-authored by Robert Shaw
parent e24663c5a9
commit 6874638bc4
7 changed files with 855 additions and 3 deletions
+5
View File
@@ -410,3 +410,8 @@ void qr_all_reduce(fptr_t _fa, torch::Tensor& inp, torch::Tensor& out,
int64_t quant_level, bool cast_bf2half = false);
int64_t qr_max_size();
#endif
#ifndef USE_ROCM
void dsv3_fused_a_gemm(torch::Tensor& output, torch::Tensor const& mat_a,
torch::Tensor const& mat_b);
#endif