models : deduplicate delta-net graphs for Qwen family (#19597)

* models : add llm_build_delta_net_base

* cont : keep qwen35 and qwen35moe graphs intact

* cont : add comments
This commit is contained in:
Georgi Gerganov
2026-02-16 14:35:04 +02:00
committed by GitHub
parent d5dfc33027
commit cc45f2ada6
16 changed files with 428 additions and 392 deletions
+1 -1
View File
@@ -2,7 +2,7 @@
llm_build_granite_hybrid::llm_build_granite_hybrid(const llama_model & model, const llm_graph_params & params) :
llm_graph_context_mamba(params) {
llm_build_mamba_base(params) {
const int64_t n_embd_head = hparams.n_embd_head_v;
GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);