nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

server: bug fix for preserved_tokens not preserved in process_token (#926) 

Co-authored-by: firecoperana <firecoperana>
This commit is contained in:
firecoperana 2025-11-09 12:16:29 +00:00 committed by GitHub
parent b63309a918
commit 73c28dbef4
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/server.cpp
View File

@ -1969,7 +1969,7 @@ struct server_context {
bool process_token(completion_token_output & result, server_slot & slot) {
// remember which tokens were sampled - used for repetition penalties during sampling
const std::string token_str = llama_token_to_piece(ctx, result.tok, params.special);
const std::string token_str = result.text_to_send;
slot.sampled = result.tok;
// search stop word and delete it
@ -3442,7 +3442,7 @@ struct server_context {
completion_token_output result;
result.tok = ids[i];
result.text_to_send = llama_token_to_piece(ctx, result.tok, params.special);
result.text_to_send = llama_token_to_piece(ctx, result.tok, accept_special_token(slot, result.tok));
result.prob = 1.0f; // set later
if (slot.sparams.n_probs > 0) {