mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

ggml: add GATED_DELTA_NET op (#19504)

Browse Source 
* 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>
This commit is contained in:
Aman Gupta
2026-03-07 15:41:10 +08:00
committed by GitHub
parent 6fce5c6a7d
commit c5a778891b
15 changed files with 627 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/include/ggml.h
+10
View File
@@ -556,6 +556,7 @@ extern "C" {
GGML_OP_GATED_LINEAR_ATTN,
GGML_OP_RWKV_WKV7,
GGML_OP_SOLVE_TRI,
GGML_OP_GATED_DELTA_NET,
GGML_OP_UNARY,
@@ -2463,6 +2464,15 @@ extern "C" {
bool lower,
bool uni);
GGML_API struct ggml_tensor * ggml_gated_delta_net(
struct ggml_context * ctx,
struct ggml_tensor * q,
struct ggml_tensor * k,
struct ggml_tensor * v,
struct ggml_tensor * g,
struct ggml_tensor * beta,
struct ggml_tensor * state);
// custom operators
typedef void (*ggml_custom1_op_t)(struct ggml_tensor * dst , const struct ggml_tensor * a, int ith, int nth, void * userdata);