ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 15:14:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

This seems to work

Browse Source
This commit is contained in:
Saood Karim
2025-08-30 04:45:31 -05:00
parent f529c3a808
commit 640f9b6485
2 changed files with 28 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@@ -2572,7 +2572,7 @@ struct server_context {
GGML_ASSERT(slot.ga_n == 1);
// reuse any previously computed tokens that are common with the new prompt
slot.n_past = common_part(slot.cache_tokens, prompt_tokens);
slot.n_past = common_part(ctx, model, slot.cache_tokens, slot.prompt);
// push the prompt into the sampling context (do not apply grammar)
for (int i = 0; i < slot.n_past; ++i) {