jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

server : consolidate slot selection into get_available_slot (#24755)

Browse Source 
Absorb get_slot_by_id logic into get_available_slot so slot selection
is handled by a single function call. When a specific slot id is
requested, the LCP similarity check still runs to enable proper
prompt cache updates.

Assisted-by: pi:llama.cpp/Qwen3.6-27B
This commit is contained in:
Georgi Gerganov 2026-06-19 09:22:34 +03:00 committed by GitHub
parent 8141e730f1
commit 80452d65b9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
tools/server/server-context.cpp
View File

@ -1395,11 +1395,23 @@ private:
bool update_cache = false; bool update_cache = false;
// if a specific slot is requested, use it (still goes through cache update logic below)
if (task.id_slot != -1) {
ret = get_slot_by_id(task.id_slot);
if (ret) {
SLT_INF(*ret, "selected slot by id (%d)\n", task.id_slot);
}
}
// find the slot that has at least n% prompt similarity // find the slot that has at least n% prompt similarity
if (ret == nullptr && slot_prompt_similarity != 0.0f) { if (slot_prompt_similarity != 0.0f) {
float sim_best = 0; float sim_best = 0;
for (server_slot & slot : slots) { for (server_slot & slot : slots) {
if (task.id_slot != -1 && slot.id != task.id_slot) {
continue;
}
// skip the slot if it is not available // skip the slot if it is not available
if (slot.is_processing()) { if (slot.is_processing()) {
continue; continue;
@ -1426,8 +1438,10 @@ private:
if (ret != nullptr) { if (ret != nullptr) {
const float f_keep = (sim_best*task.tokens.size()) / ret->prompt.tokens.size(); const float f_keep = (sim_best*task.tokens.size()) / ret->prompt.tokens.size();
SLT_INF(*ret, "selected slot by LCP similarity, sim_best = %.3f (> %.3f thold), f_keep = %.3f\n", if (task.id_slot == -1) {
sim_best, slot_prompt_similarity, f_keep); SLT_INF(*ret, "selected slot by LCP similarity, sim_best = %.3f (> %.3f thold), f_keep = %.3f\n",
sim_best, slot_prompt_similarity, f_keep);
}
// if we are about to lose a large portion of the existing context - save it in the prompt cache // if we are about to lose a large portion of the existing context - save it in the prompt cache
if (f_keep < 0.5f) { if (f_keep < 0.5f) {
@ -2180,10 +2194,9 @@ private:
} }
} }
const int id_slot = task.id_slot;
const int id_task = task.id; const int id_task = task.id;
server_slot * slot = id_slot != -1 ? get_slot_by_id(id_slot) : get_available_slot(task); server_slot * slot = get_available_slot(task);
// //
// slot scheduling logic // slot scheduling logic