Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 17:24:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

nits

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-26 21:22:49 +02:00
parent c0ea2b3038
commit d07a0ae352
2 changed files with 0 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache.cpp
-5
View File
@@ -12,7 +12,6 @@
#include <limits>
#include <map>
#include <stdexcept>
#include <unordered_map>
static bool ggml_is_power_of_2(int n) {
return (n & (n - 1)) == 0;
@@ -2670,7 +2669,3 @@ void llama_kv_cache_context::set_input_k_rot(ggml_tensor * dst) const {
void llama_kv_cache_context::set_input_v_rot(ggml_tensor * dst) const {
kv->set_input_v_rot(dst);
}
void llama_kv_cache_context::get_prev_tokens(const llama_ubatch & ubatch, uint32_t n, std::vector<llama_token> & res) const {
kv->get_prev_tokens(ubatch, n, res);
}
src/llama-kv-cache.h
-3
View File
@@ -404,9 +404,6 @@ public:
void set_input_k_rot(ggml_tensor * dst) const;
void set_input_v_rot(ggml_tensor * dst) const;
// see llama_kv_cache::get_prev_tokens()
void get_prev_tokens(const llama_ubatch & ubatch, uint32_t n, std::vector<llama_token> & res) const;
private:
llama_memory_status status;