talk-llama : sync llama.cpp

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-01 10:43:30 +03:00
parent 5cd59c9396
commit 0778b6ff5f
13 changed files with 159 additions and 74 deletions

View File

@@ -66,6 +66,7 @@ struct llama_hparams {
float expert_weights_scale = 0.0;
bool expert_weights_norm = false;
uint32_t expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_NONE;
uint32_t moe_every_n_layers = 0;
float f_norm_eps;
float f_norm_rms_eps;