vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add queue info

Browse source
This commit is contained in:
Concedo 2023-09-20 21:07:21 +08:00
parent 0eb52cf6c2
commit b63cf223c9
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
koboldcpp.py
View file

@ -555,7 +555,7 @@ class ServerRequestHandler(http.server.SimpleHTTPRequestHandler):
laste = handle.get_last_eval_time() laste = handle.get_last_eval_time()
lastc = handle.get_last_token_count() lastc = handle.get_last_token_count()
stopreason = handle.get_last_stop_reason() stopreason = handle.get_last_stop_reason()
response_body = (json.dumps({"last_process":lastp,"last_eval":laste,"last_token_count":lastc, "stop_reason":stopreason, "idle":(0 if modelbusy.locked() else 1)}).encode()) response_body = (json.dumps({"last_process":lastp,"last_eval":laste,"last_token_count":lastc, "stop_reason":stopreason, "queue":requestsinqueue, "idle":(0 if modelbusy.locked() else 1)}).encode())
if response_body is None: if response_body is None:
self.send_response(404) self.send_response(404)