mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

llama: dynamic head_dim and n_rot for SWA (#20301)

Browse Source 
* llama: dynamic head_dim and n_rot for SWA

* also add gguf_writer wrappers

* fix build

* build_rope_shift arg reorder
This commit is contained in:
Xuan-Son Nguyen
2026-03-09 22:22:39 +01:00
committed by GitHub
parent 23fbfcb1ad
commit 59db9a357d
112 changed files with 419 additions and 346 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/plamo3.cpp
+2 -2
View File
@@ -3,8 +3,8 @@
template <bool iswa>
llm_build_plamo3<iswa>::llm_build_plamo3(const llama_model & model, const llm_graph_params & params) :
llm_graph_context(params) {
const int64_t head_dim_q = hparams.n_embd_head_k;
const int64_t head_dim_v = hparams.n_embd_head_v;
const int64_t head_dim_q = hparams.n_embd_head_k();
const int64_t head_dim_v = hparams.n_embd_head_v();
ggml_tensor * cur;
ggml_tensor * inpL = build_inp_embd(model.tok_embd);