vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-07-27 09:43:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

quant : fix quantizing moe with mtp (#24986)

Browse source
This commit is contained in:
Sigbjørn Skjæret 2026-06-25 07:36:49 +02:00 • committed by GitHub
parent e9fb3b3fc0
commit b3ce5cedf4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-quant.cpp
View file

@ -847,7 +847,7 @@ static void init_quantize_state_counters(quantize_state_impl & qs, std::vector<t
qs.has_tied_embeddings = false;
}
}
qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer();
qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer_all;
}
//