tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-29 05:33:37 -04:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : use ggml_set_rows (#14285)

Browse Source 
* kv-cache : use ggml_set_rows

ggml-ci

* graph : separate k and v indices

ggml-ci

* cont : remove redundant ifs

ggml-ci

* kv-cache : improve find_slot impl

* kv-cache : bounds-check when accessing slot_info indices

* kv-cache : add comments

ggml-ci

* ggml : add TODOs for adding GGML_OP_SET_ROWS support in the backends

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-03 10:53:35 +03:00
committed by GitHub
parent 9067487c44
commit a70c8a0c4b
13 changed files with 451 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/llama-kv-cache-unified-iswa.h
View File

@@ -74,6 +74,8 @@ private:
class llama_kv_cache_unified_iswa_context : public llama_memory_context_i {
public:
using slot_info_vec_t = llama_kv_cache_unified::slot_info_vec_t;
// used for errors
llama_kv_cache_unified_iswa_context(llama_memory_status status);
@@ -90,8 +92,8 @@ public:
// used to create a batch processing context from a batch
llama_kv_cache_unified_iswa_context(
llama_kv_cache_unified_iswa * kv,
std::vector<uint32_t> heads_base,
std::vector<uint32_t> heads_swa,
slot_info_vec_t sinfos_base,
slot_info_vec_t sinfos_swa,
std::vector<llama_ubatch> ubatches);
virtual ~llama_kv_cache_unified_iswa_context();