LLM inference in C/C++
C++ ggml
quant : fix quantizing moe with mtp (#24986)
Sigbjørn Skjæretb3ce5cedf4c0
diff --git a/src/llama-quant.cpp b/src/llama-quant.cppindex 89b7fe8d43..847e79f465 100644--- a/src/llama-quant.cpp+++ b/src/llama-quant.cpp@@ -847,7 +847,7 @@ static void init_quantize_state_counters(quantize_state_impl & qs, std::vector<tqs.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;}//