ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-24 00:19:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

server: stop processing the prompt when client disconnects (#1134)

Browse Source 
implement generator-based API for task results

Update httplib.h to 0.27.0

Fix embedding error

Stop prompt processing when disconnected

Co-authored-by: firecoperana <firecoperana>
This commit is contained in:
firecoperana
2026-01-12 23:56:59 -06:00
committed by GitHub
parent d3e3ad40f9
commit 1a461525d5
24 changed files with 7654 additions and 4549 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
common/common.cpp
View File

@@ -3775,7 +3775,7 @@ void llama_kv_cache_dump_view_seqs(const llama_kv_cache_view & view, int row_siz
// Embedding utils
//
void llama_embd_normalize(const float * inp, float * out, int n, int embd_norm) {
void common_embd_normalize(const float * inp, float * out, int n, int embd_norm) {
double sum = 0.0;
switch (embd_norm) {
@@ -3809,7 +3809,7 @@ void llama_embd_normalize(const float * inp, float * out, int n, int embd_norm)
}
}
float llama_embd_similarity_cos(const float * embd1, const float * embd2, int n){
float common_embd_similarity_cos(const float * embd1, const float * embd2, int n){
double sum = 0.0;
double sum1 = 0.0;
double sum2 = 0.0;