vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-30 20:33:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

models : Attach Mistral3 NVFP4 weight scales (#23629)

Browse source
This commit is contained in:
Michael Wand 2026-05-26 00:59:59 -04:00 • committed by GitHub
parent 581d020b12
commit 6fe90deffa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 8 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

12
src/models/mistral3.cpp
View file

@ -177,9 +177,9 @@ llama_model_mistral3::graph::graph(const llama_model & model, const llm_graph_pa
cb(cur, "ffn_norm", il);
cur = build_ffn(cur,
model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL,
model.layers[il].ffn_gate, model.layers[il].ffn_gate_b, NULL,
model.layers[il].ffn_down, model.layers[il].ffn_down_b, NULL,
model.layers[il].ffn_up, model.layers[il].ffn_up_b, model.layers[il].ffn_up_s,
model.layers[il].ffn_gate, model.layers[il].ffn_gate_b, model.layers[il].ffn_gate_s,
model.layers[il].ffn_down, model.layers[il].ffn_down_b, model.layers[il].ffn_down_s,
NULL,
LLM_FFN_SILU, LLM_FFN_PAR, il);
cb(cur, "ffn_out", il);
@ -200,7 +200,11 @@ llama_model_mistral3::graph::graph(const llama_model & model, const llm_graph_pa
LLM_FFN_SILU, true,
hparams.expert_weights_scale,
LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX,
il);
il,
nullptr, nullptr,
model.layers[il].ffn_up_exps_s,
model.layers[il].ffn_gate_exps_s,
model.layers[il].ffn_down_exps_s);
cb(cur, "ffn_moe_out", il);
}
cur = ggml_add(ctx0, cur, ffn_inp);