upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-05 17:40:46 -05:00
Code Issues Packages Projects Releases Wiki Activity

mimo2: address MTP review feedback (#26228)

Browse Source 
Co-authored-by: tnhnyc <115956684+tnhnyc@users.noreply.github.com>
This commit is contained in:
Tunahan
2026-07-30 05:55:58 +02:00
committed by GitHub
parent 3018a11e79
commit 64d528be72
4 changed files with 191 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-model.cpp
View File

@@ -2243,7 +2243,9 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
filter = [&](uint32_t il) { return il >= hparams.n_layer(); };
}
if ((arch == LLM_ARCH_STEP35 || arch == LLM_ARCH_HY_V3 || arch == LLM_ARCH_GLM_DSA) && hparams.n_layer_nextn > 0) {
if ((arch == LLM_ARCH_STEP35 || arch == LLM_ARCH_HY_V3 || arch == LLM_ARCH_GLM_DSA ||
arch == LLM_ARCH_MIMO2) &&
hparams.n_layer_nextn > 0) {
if (params.ctx_type == LLAMA_CONTEXT_TYPE_MTP) {
filter = [&](uint32_t il) { return il >= hparams.n_layer(); };
} else {