ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

ggml : fix multi-threaded clamp_f32 (#11824)

Browse source 
* Bug fix for clamp_f32

When using tensors larger than 1d clamp operation does not work due to the restriction of returning if ith is not 0.

* Bug fix for clamp_f32

* Bug fix for clamp_f32
This commit is contained in:
Richard 2025-02-12 13:57:33 +00:00 • committed by GitHub
parent 198b1ec611
commit 748ee9fe93
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 0 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml/src/ggml-cpu/ggml-cpu.c
View file

@ -9074,10 +9074,6 @@ static void ggml_compute_forward_clamp_f32(
const struct ggml_tensor * src0 = dst->src[0]; const struct ggml_tensor * src0 = dst->src[0];
if (params->ith != 0) {
return;
}
float min; float min;
float max; float max;
memcpy(&min, (float *) dst->op_params + 0, sizeof(float)); memcpy(&min, (float *) dst->op_params + 0, sizeof(float));