LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

model : load MiMo V2 MTP tensors only if used (#26412)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2026-08-02 09:03:05 +02:00
committed by GitHub
parent 7a2db1a0cf
commit 75587a05b3
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/mimo2.cpp
+5 -1
View File
@@ -30,7 +30,11 @@ void llama_model_mimo2::load_arch_tensors(llama_model_loader & ml) {
const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight";
const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr);
const int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0;
int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0;
if (!ml.load_mtp) {
mtp_flags |= TENSOR_SKIP;
}
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);