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

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

4
include/llama.h
View file

@ -64,8 +64,6 @@ extern "C" {
typedef struct llama_memory_i * llama_memory_t;
struct llama_kv_cache; // DEPRECATED (use llama_memory instead)
typedef int32_t llama_pos;
typedef int32_t llama_token;
typedef int32_t llama_seq_id;
@ -469,8 +467,6 @@ extern "C" {
LLAMA_API llama_memory_t llama_get_memory (const struct llama_context * ctx);
LLAMA_API enum llama_pooling_type llama_pooling_type(const struct llama_context * ctx); // TODO: rename to llama_get_pooling_type
DEPRECATED(LLAMA_API struct llama_kv_cache * llama_get_kv_self(struct llama_context * ctx), "use llama_get_memory instead");
LLAMA_API const struct llama_vocab * llama_model_get_vocab(const struct llama_model * model);
LLAMA_API enum llama_rope_type llama_model_rope_type(const struct llama_model * model);