mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 31 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/llama-graph.cpp
+3 -3
View File
@@ -849,13 +849,13 @@ llm_graph_context::llm_graph_context(const llm_graph_params & params) :
ubatch (params.ubatch),
n_embd (hparams.n_embd),
n_layer (hparams.n_layer),
n_rot (hparams.n_rot),
n_rot (hparams.n_rot()),
n_ctx (cparams.n_ctx),
n_head (hparams.n_head()),
n_head_kv (hparams.n_head_kv()),
n_embd_head_k (hparams.n_embd_head_k),
n_embd_head_k (hparams.n_embd_head_k()),
n_embd_k_gqa (hparams.n_embd_k_gqa()),
n_embd_head_v (hparams.n_embd_head_v),
n_embd_head_v (hparams.n_embd_head_v()),
n_embd_v_gqa (hparams.n_embd_v_gqa()),
n_expert (hparams.n_expert),
n_expert_used (cparams.warmup ? hparams.n_expert : hparams.n_expert_used),