model: add MTP support for Nemotron model (#26725)

* model: add MTP support for Nemotron Nano model

* model: add mtp_flags for nemotron model

* address review comments
This commit is contained in:
Ruixiang Wang authored and GitHub committed 2026-08-10 11:25:24 +03:00
1 parent e23e9440eb
commit 7a20b417f4
6 files changed
+309 -33

No files matched your search

+4
View File
@@ -1461,6 +1461,10 @@ struct llama_model_nemotron_h_moe : public llama_model_nemotron_h {
using graph = llama_model_nemotron_h::graph;
struct graph_mtp : public llm_graph_context {
graph_mtp(const llama_model & model, const llm_graph_params & params);
};
std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
};