mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-04-16 03:26:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama.cpp: fix warning message (#11839)

Browse Source 
There was a typo-like error, which would print the same number twice if
request is received with n_predict > server-side config.

Before the fix:
```
slot launch_slot_: id  0 | task 0 | n_predict = 4096 exceeds server configuration, setting to 4096
```

After the fix:
```
slot launch_slot_: id  0 | task 0 | n_predict = 8192 exceeds server configuration, setting to 4096
```
This commit is contained in:
Oleksandr Kuvshynov 2025-02-13 01:25:34 -05:00 committed by GitHub
parent 3e69319772
commit e4376270d9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -2073,8 +2073,8 @@ struct server_context {
if (slot.n_predict > 0 && slot.params.n_predict > slot.n_predict) {
// Might be better to reject the request with a 400 ?
SLT_WRN(slot, "n_predict = %d exceeds server configuration, setting to %d", slot.params.n_predict, slot.n_predict);
slot.params.n_predict = slot.n_predict;
SLT_WRN(slot, "n_predict = %d exceeds server configuration, setting to %d", slot.n_predict, slot.n_predict);
}
if (slot.params.ignore_eos && has_eos_token) {