kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-09 12:40:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

logs : reduce v2 (#25078)

Browse Source 
* server : reduce logs

* cont : common

* cont : spec

* cont : CMN_ -> COM_
This commit is contained in:
Georgi Gerganov
2026-06-28 08:52:15 +03:00
committed by GitHub
parent ebd048fc5e
commit 27c8bb4f63
12 changed files with 203 additions and 194 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-task.cpp
+6 -6
View File
@@ -1626,7 +1626,7 @@ server_prompt * server_prompt_cache::alloc(const server_prompt & prompt, size_t
const int cur_lcp_len = it->tokens.get_common_prefix(prompt.tokens);
if (cur_lcp_len == (int) prompt.tokens.size()) {
SRV_INF("%s", " - prompt is already in the cache, skipping\n");
SRV_TRC("%s", " - prompt is already in the cache, skipping\n");
return nullptr;
}
}
@@ -1636,7 +1636,7 @@ server_prompt * server_prompt_cache::alloc(const server_prompt & prompt, size_t
const int len = it->tokens.get_common_prefix(prompt.tokens);
if (len == (int) it->tokens.size()) {
SRV_WRN(" - removing obsolete cached prompt with length %d\n", len);
SRV_TRC(" - removing obsolete cached prompt with length %d\n", len);
it = states.erase(it);
} else {
@@ -1681,7 +1681,7 @@ bool server_prompt_cache::load(server_prompt & prompt, const server_tokens & tok
float f_keep_best = prompt.tokens.size() > 0 ? float(lcp_best) / prompt.tokens.size() : -1.0f; // empty slot: any cache entry wins
float sim_best = float(lcp_best) / tokens_new.size();
SRV_INF(" - looking for better prompt, base f_keep = %.3f, sim = %.3f\n", f_keep_best, sim_best);
SRV_TRC(" - looking for better prompt, base f_keep = %.3f, sim = %.3f\n", f_keep_best, sim_best);
auto it_best = states.end();
@@ -1706,7 +1706,7 @@ bool server_prompt_cache::load(server_prompt & prompt, const server_tokens & tok
}
if (it_best != states.end()) {
SRV_INF(" - found better prompt with f_keep = %.3f, sim = %.3f\n", f_keep_best, sim_best);
SRV_TRC(" - found better prompt with f_keep = %.3f, sim = %.3f\n", f_keep_best, sim_best);
{
auto & data = it_best->data.main;
@@ -1783,11 +1783,11 @@ void server_prompt_cache::update() {
}
}
SRV_INF(" - cache state: %zu prompts, %.3f MiB (limits: %.3f MiB, %zu tokens, %zu est)\n",
SRV_TRC(" - cache state: %zu prompts, %.3f MiB (limits: %.3f MiB, %zu tokens, %zu est)\n",
states.size(), size() / (1024.0 * 1024.0), limit_size / (1024.0 * 1024.0), limit_tokens, limit_tokens_cur);
for (const auto & state : states) {
SRV_INF(" - prompt %p: %7d tokens, checkpoints: %2zu, %9.3f MiB\n",
SRV_TRC(" - prompt %p: %7d tokens, checkpoints: %2zu, %9.3f MiB\n",
(const void *)&state, state.n_tokens(), state.checkpoints.size(), state.size() / (1024.0 * 1024.0));
}
}