thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

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

Browse source 
* 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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 428 additions and 392 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/models/nemotron-h.cpp
View file

@ -1,9 +1,7 @@
#include "models.h"
llm_build_nemotron_h::llm_build_nemotron_h(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);
@ -65,8 +63,8 @@ llm_build_nemotron_h::llm_build_nemotron_h(const llama_model & model, const llm_
ggml_tensor * llm_build_nemotron_h::build_attention_layer(ggml_tensor * cur,
llm_graph_input_attn_kv * inp_attn,
const llama_model & model,
const int64_t n_embd_head,
const int il) {
int64_t n_embd_head,
int il) {
// compute Q and K
ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
cb(Qcur, "Qcur", il);
@ -106,7 +104,7 @@ ggml_tensor * llm_build_nemotron_h::build_attention_layer(ggml_tensor *
return cur;
}
ggml_tensor * llm_build_nemotron_h::build_ffn_layer(ggml_tensor * cur, const llama_model & model, const int il) {
ggml_tensor * llm_build_nemotron_h::build_ffn_layer(ggml_tensor * cur, const llama_model & model, int il) {
if (model.layers[il].ffn_gate_inp == nullptr) {
cur = build_ffn(cur,
model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL,