CUDA: use shared mem for ssm_conv (#20128)

* CUDA: use shared mem for ssm_conv * fuse silu + ssm_conv * fuse unary + mul * enable for fp16 * formatting Co-authored-by: Johannes Gäßler <johannesg@5d6.de> --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2026-03-06 23:09:59 +08:00
parent 388baabc06
commit 1e38a7a6fa
6 changed files with 168 additions and 33 deletions
@@ -89,6 +89,8 @@ void ggml_cuda_op_geglu_quick(ggml_backend_cuda_context & ctx, ggml_tensor * dst

 void ggml_cuda_op_xielu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

+void ggml_cuda_op_unary_mul(ggml_backend_cuda_context & ctx, ggml_tensor * unary_node, ggml_tensor * mul_node);
+
 __device__ __forceinline__ float ggml_cuda_op_silu_single(float x) {
    return x / (1.0f + expf(-x));
 }