ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-21 21:54:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Vulkan: add GGML_OP_FUSED_MUL_UNARY (#580)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-07-03 18:03:23 +02:00
committed by GitHub
parent b445c83eb9
commit 8d4f0a61db
6 changed files with 142 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/llama.cpp
View File

@@ -9688,13 +9688,7 @@ static struct ggml_tensor * llm_build_ffn(
cur = tmp;
}
#ifdef GGML_USE_VULKAN
constexpr bool use_fused_mul_unary = false;
#else
constexpr bool use_fused_mul_unary = true;
#endif
if (use_fused_mul_unary && type_gate == LLM_FFN_PAR &&
if (type_gate == LLM_FFN_PAR &&
(type_op == LLM_FFN_SILU || type_op == LLM_FFN_RELU || (type_op == LLM_FFN_GELU && !act_scales))) {
cur = ggml_fused_mul_unary(ctx, cur, tmp, type_op == LLM_FFN_SILU ? GGML_UNARY_OP_SILU :
type_op == LLM_FFN_RELU ? GGML_UNARY_OP_RELU : GGML_UNARY_OP_GELU);