LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

server : add extra trace log for prompt similarity (#26218)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-07-28 11:05:16 +03:00
committed by GitHub
parent f95de9776b
commit 9a3bf2b849
2 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-task.cpp
+2
View File
@@ -1755,6 +1755,8 @@ bool server_prompt_cache::load(server_prompt & prompt, const server_tokens & tok
const float f_keep_cur = float(lcp_cur) / it->prompt.tokens.size();
const float sim_cur = float(lcp_cur) / tokens_new.size();
SRV_TRC(" - prompt with length %7zu, lcp = %7d, f_keep = %.3f, sim = %.3f\n", it->prompt.tokens.size(), lcp_cur, f_keep_cur, sim_cur);
// don't trash large prompts
if (f_keep_cur < 0.25f) {
continue;
tools/server/server-task.h
+1 -1
View File
@@ -650,7 +650,7 @@ struct server_prompt_cache {
server_prompt_cache_state * alloc(const server_prompt & prompt, size_t state_size_main, size_t state_size_drft);
bool load(server_prompt & prompt, const server_tokens & tokens_new, llama_context * ctx_main, llama_context * ctx_drft, int32_t id_slot);
bool load(server_prompt & prompt, const server_tokens & tokens_new, llama_context * ctx_tgt, llama_context * ctx_dft, int32_t id_slot);
void update();
};