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

metal : fix yarn (#4220)

Browse source 
get the correct n_orig_ctx in metal
This commit is contained in:
Xiao-Yong Jin 2023-11-26 02:30:02 -06:00 committed by GitHub
parent 1ddb52ec38
commit 22da05536f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
ggml-metal.m
View file

@ -1433,7 +1433,8 @@ void ggml_metal_graph_compute(
const int n_past = ((int32_t *) dst->op_params)[0];
const int n_dims = ((int32_t *) dst->op_params)[1];
const int mode = ((int32_t *) dst->op_params)[2];
const int n_orig_ctx = ((int32_t *) dst->op_params)[3];
// skip 3, n_ctx, used in GLM RoPE, unimplemented in metal
const int n_orig_ctx = ((int32_t *) dst->op_params)[4];
float freq_base, freq_scale, ext_factor, attn_factor, beta_fast, beta_slow;
memcpy(&freq_base, (int32_t *) dst->op_params + 5, sizeof(float));