CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-13 10:57:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : handle failures to restore host cache (#17078)

Browse Source 
* server : handle failures to restore host cache

* server : add tests for the prompt cache
This commit is contained in:
Georgi Gerganov
2025-11-09 14:27:05 +02:00
committed by GitHub
parent ef1d826997
commit cb1adf8851
2 changed files with 45 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tools/server/server.cpp
View File

@@ -1690,6 +1690,9 @@ struct server_slot {
bool res = prompt_cache.load(prompt, tokens, ctx, id);
if (!res) {
SLT_WRN(*this, "%s", "failed to load prompt from cache\n");
llama_memory_seq_rm(llama_get_memory(ctx), id, -1, -1);
prompt.tokens.clear();
}
}