thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

kv-cache : drop the "unified" prefix (#15467)

Browse source 
* kv-cache : drop the "unified" prefix

ggml-ci

* cont : fix comment [no ci]
This commit is contained in:
Georgi Gerganov 2025-08-21 17:00:33 +03:00 • committed by GitHub
parent ad294df03f
commit 715a6db02c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 346 additions and 360 deletions
Download patch file Download diff file Expand all files Collapse all files

5
src/llama-context.cpp
View file

@ -2338,11 +2338,6 @@ const llama_model * llama_get_model(const llama_context * ctx) {
return &ctx->get_model();
}
// deprecated
llama_kv_cache * llama_get_kv_self(llama_context * ctx) {
return dynamic_cast<llama_kv_cache *>(ctx->get_memory());
}
// deprecated
void llama_kv_self_update(llama_context * ctx) {
ctx->kv_self_update(false);