CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 (#15131)

* CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16
2025-08-07 10:53:21 +02:00
parent 20638e4f16
commit 1d72c84188
13 changed files with 750 additions and 225 deletions
@@ -0,0 +1,11 @@
+#include "common.cuh"
+
+void ggml_cuda_mul_mat_vec_f(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * ids, ggml_tensor * dst);
+
+void ggml_cuda_op_mul_mat_vec_f(
+    ggml_backend_cuda_context & ctx,
+    const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const char * src0_dd_i, const float * src1_ddf_i,
+    const char * src1_ddq_i, float * dst_dd_i, const int64_t row_low, const int64_t row_high, const int64_t src1_ncols,
+    const int64_t src1_padded_row_size, cudaStream_t stream);
+
+bool ggml_cuda_should_use_mmvf(enum ggml_type type, int cc, const int64_t * src0_ne, int64_t ne11);