ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : fix Gemma3 SWA KV cache shift (#12373)

Browse source 
* llama : fix Gemma3 SWA KV cache shift

ggml-ci

* hparams : add comment [no ci]
This commit is contained in:
Georgi Gerganov 2025-03-13 19:08:07 +02:00 • committed by GitHub
parent be7c303410
commit 84d5475541
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 37 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-context.h
View file

@ -168,6 +168,8 @@ private:
ggml_tensor * cur,
ggml_tensor * shift,
ggml_tensor * factors,
float freq_base,
float freq_scale,
ggml_backend_buffer * bbuf) const;
llm_graph_result_ptr build_kv_self_shift(