tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : do not return error out of context (with ctx shift disabled) (#13577)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2025-05-16 21:50:00 +02:00
committed by GitHub
parent aea9f8b4e7
commit 6aa892ec2a
2 changed files with 26 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tools/server/server.cpp
View File

@ -2251,6 +2251,14 @@ struct server_context {
slot.has_next_token = true;
}
// if context shifting is disabled, make sure that we don't run out of context
if (!params_base.ctx_shift && slot.n_past + 1 >= slot.n_ctx) {
slot.stop = STOP_TYPE_LIMIT;
slot.has_next_token = false;
SLT_DBG(slot, "stopped due to running out of context, n_past = %d, n_ctx = %d\n", slot.n_past, slot.n_ctx);
}
// check the limits
if (slot.n_decoded > 0 && slot.has_next_token && !slot.has_budget(params_base)) {
slot.stop = STOP_TYPE_LIMIT;