Aman GuptaandGeorgi Gerganov
c5a778891b
* ggml: add GATED_DELTA_NET op * remove the transpose * add KDA * add qwen35 dense * llama : check for fused gated delta net backend support --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
5 lines
128 B
Plaintext
5 lines
128 B
Plaintext
#include "common.cuh"
|
|
#include "ggml.h"
|
|
|
|
void ggml_cuda_op_gated_delta_net(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|