CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-14 11:07:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : remove KV cache defragmentation logic (#15473)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-08-22 12:22:13 +03:00
committed by GitHub
parent ad5c975c2d
commit 9ebebef62f
16 changed files with 32 additions and 440 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
src/llama-kv-cells.h
View File

@@ -77,24 +77,24 @@ public:
}
// move cell isrc to idst (used during defrag)
void mv(uint32_t isrc, uint32_t idst) {
assert(isrc < pos.size());
assert(idst < pos.size());
//void mv(uint32_t isrc, uint32_t idst) {
// assert(isrc < pos.size());
// assert(idst < pos.size());
assert(pos[idst] == -1);
assert(pos[isrc] != -1);
// assert(pos[idst] == -1);
// assert(pos[isrc] != -1);
pos [idst] = pos [isrc];
shift[idst] = shift[isrc];
seq [idst] = seq [isrc];
// pos [idst] = pos [isrc];
// shift[idst] = shift[isrc];
// seq [idst] = seq [isrc];
pos [isrc] = -1;
shift[isrc] = 0;
seq [isrc].reset();
// pos [isrc] = -1;
// shift[isrc] = 0;
// seq [isrc].reset();
used.erase (isrc);
used.insert(idst);
}
// used.erase (isrc);
// used.insert(idst);
//}
// copy the state of cells [i, i + n) (used for save/restore the state of the cells)
llama_kv_cells cp(uint32_t i, uint32_t n) const {