CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : remove LLAMA_SET_ROWS checks (#15505)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-08-28 12:27:02 +03:00
committed by GitHub
parent 64387f6e95
commit 8a4280ce43
7 changed files with 23 additions and 141 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/llama-kv-cache.h
View File

@@ -141,9 +141,6 @@ public:
uint32_t get_n_kv(const slot_info & sinfo) const;
// TODO: temporary
bool get_supports_set_rows() const;
// get views of the current state of the cache
ggml_tensor * get_k(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const;
ggml_tensor * get_v(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const;
@@ -215,10 +212,6 @@ private:
// env: LLAMA_KV_CACHE_DEBUG
int debug = 0;
// env: LLAMA_SET_ROWS (temporary)
// ref: https://github.com/ggml-org/llama.cpp/pull/14285
bool supports_set_rows = true;
const llama_swa_type swa_type = LLAMA_SWA_TYPE_NONE;
std::vector<ggml_context_ptr> ctxs;
@@ -318,9 +311,6 @@ public:
uint32_t get_n_kv() const;
// TODO: temporary
bool get_supports_set_rows() const;
// get views of the current state of the cache
ggml_tensor * get_k(ggml_context * ctx, int32_t il) const;
ggml_tensor * get_v(ggml_context * ctx, int32_t il) const;