Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-29 07:34:18 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix cur -> cur_expert

Browse Source
This commit is contained in:
Georgi Gerganov 2023-12-09 12:07:39 +02:00
parent aedfad120a
commit af1a096bf8
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@ -4269,7 +4269,7 @@ struct llm_build_context {
ggml_mul_mat_id(ctx0, ffn_gate_exp, selected_experts, i, cur))); // [n_tokens, n_embd]
cur_expert = ggml_mul_mat_id(ctx0, ffn_down_exp, selected_experts, i, cur_expert); // [n_tokens, n_embd]
cur_expert = ggml_mul(ctx0, cur,
cur_expert = ggml_mul(ctx0, cur_expert,
ggml_view_2d(ctx0, weights, 1, n_tokens, weights->nb[1], i*weights->nb[0]));
if (i == 0) {