wmantly/llama.cpp-xrip
1
0 Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

quant : fix quantizing moe with mtp (#24986)

Browse Source
This commit is contained in:
Sigbjørn Skjæret authored and GitHub committed 2026-06-25 08:36:49 +03:00
1 parent e9fb3b3fc0
commit b3ce5cedf4
1 file changed
+1 -1
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;
}
//