CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : sync (unary ops refactor, static-correctness) (#2370)

Browse Source 
* ggml : sync (unary ops, tests)

ggml-ci

* tests : remove unnecessary funcs
This commit is contained in:
Georgi Gerganov
2023-07-24 14:46:21 +03:00
committed by GitHub
parent 42f70cb2f6
commit 5b2b2dc6ae
6 changed files with 867 additions and 572 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
ggml-cuda.cu
View File

@@ -3962,18 +3962,23 @@ bool ggml_cuda_compute_forward(struct ggml_compute_params * params, struct ggml_
}
func = ggml_cuda_mul;
break;
case GGML_OP_GELU:
if (!any_on_device) {
return false;
}
func = ggml_cuda_gelu;
break;
case GGML_OP_SILU:
if (!any_on_device) {
return false;
}
func = ggml_cuda_silu;
break;
case GGML_OP_UNARY:
switch (ggml_get_unary_op(tensor)) {
case GGML_UNARY_OP_GELU:
if (!any_on_device) {
return false;
}
func = ggml_cuda_gelu;
break;
case GGML_UNARY_OP_SILU:
if (!any_on_device) {
return false;
}
func = ggml_cuda_silu;
break;
default:
return false;
} break;
case GGML_OP_NORM:
if (!any_on_device) {
return false;