thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

llama : merge build_moe_ffn_from_probs function into build_moe_ffn (#14968)

Browse source
This commit is contained in:
Dongliang Wei 2025-07-31 20:12:20 +08:00 • committed by GitHub
parent a9f77a8be3
commit c1dacaa99b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 32 additions and 114 deletions
Download patch file Download diff file Expand all files Collapse all files

15
src/llama-graph.h
View file

@ -631,19 +631,8 @@ struct llm_graph_context {
bool scale_w,
float w_scale,
llama_expert_gating_func_type gating_op,
int il) const;
ggml_tensor * build_moe_ffn_from_probs(
ggml_tensor * cur,
ggml_tensor * probs,
ggml_tensor * up_exps,
ggml_tensor * gate_exps,
ggml_tensor * down_exps,
ggml_tensor * exp_probs_b,
int64_t n_expert,
int64_t n_expert_used,
llama_expert_gating_func_type gating_op,
int il) const;
int il,
ggml_tensor * probs_in = nullptr) const;
//
// inputs