ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

kv-cache : refactor the update/defrag mechanism (#13988)

Browse source 
* kv-cache : refactor update mechanism

ggml-ci

* memory : improve status handling

* defrag : reset head + add comments

ggml-ci

* cont : minor fixes

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-06-04 18:58:20 +03:00 • committed by GitHub
parent 2589ad3704
commit 3e63a58ef7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 340 additions and 191 deletions
Download patch file Download diff file Expand all files Collapse all files

41
src/llama-memory.cpp
View file

@ -1 +1,42 @@
#include "llama-memory.h"
llama_memory_status llama_memory_status_combine(llama_memory_status s0, llama_memory_status s1) {
bool has_update = false;
switch (s0) {
case LLAMA_MEMORY_STATUS_SUCCESS:
{
has_update = true;
break;
}
case LLAMA_MEMORY_STATUS_NO_UPDATE:
{
break;
}
case LLAMA_MEMORY_STATUS_FAILED_PREPARE:
case LLAMA_MEMORY_STATUS_FAILED_COMPUTE:
{
return s0;
}
}
switch (s1) {
case LLAMA_MEMORY_STATUS_SUCCESS:
{
has_update = true;
break;
}
case LLAMA_MEMORY_STATUS_NO_UPDATE:
{
break;
}
case LLAMA_MEMORY_STATUS_FAILED_PREPARE:
case LLAMA_MEMORY_STATUS_FAILED_COMPUTE:
{
return s1;
}
}
// if either status has an update, then the combined status has an update
return has_update ? LLAMA_MEMORY_STATUS_SUCCESS : LLAMA_MEMORY_STATUS_NO_UPDATE;
}