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

llama : fix Mamba-2 conv state saving

Browse source 
* ggml : make the ggml_mul fast broadcast path more consistently formatted
This commit is contained in:
Francis Couture-Harpin 2024-08-21 16:28:07 -04:00
parent 2bfe9de6d3
commit aff96920f9
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml/src/ggml.c
View file

@ -10226,11 +10226,11 @@ static void ggml_compute_forward_mul_f32(
if (scale == 0.0f) {
// NOTE: this also sets NANs to zero, which is not compliant with IEEE754,
// but it is useful when resetting the state of recurrent models.
memset((char *)dst->data + ir*nb1, 0, nb1);
memset((char *) dst->data + ir*nb1, 0, ne0 * sizeof(float));
} else {
if (dst->data != src0->data) {
// src0 is same shape as dst => same indices
memcpy((char *)dst->data + ir*nb1, (char *)src0->data + ir*nb01, ne0 * sizeof(float));
memcpy((char *) dst->data + ir*nb1, (char *) src0->data + ir*nb01, ne0 * sizeof(float));
}
if (scale != 1.0f) {
ggml_vec_scale_f32(ne0, (float *) ((char *) dst->data + ir*nb1), scale);