kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-26 06:10:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

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
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+1 -1
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;
}
//