model: apply .scale tensors automatically + fix correctness (#32669)
* model: apply .scale tensors automatically * rm build_moe_ffn "_s" overload * use llama_prec_policy * fix ci * build_lora_mm_id: rm w_s
This commit is contained in:
1 parent
e50c254a22
commit
19bc41dbb4
39 files changed
+164
-290
No files matched your search
@@ -277,9 +277,6 @@ ggml_tensor * llama_model_zaya1::graph::build_router_moe(const llama_model & mod
|
||||
il,
|
||||
logits,
|
||||
layer.ffn_gate_up_exps,
|
||||
nullptr,
|
||||
nullptr,
|
||||
nullptr,
|
||||
expert);
|
||||
|
||||
return ggml_mul(ctx0, moe, keep);
|
||||
|
||||
Reference in new issue
Block a user