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

fix indentation, increase server thread count

Browse source
This commit is contained in:
Concedo 2023-08-04 10:29:56 +08:00
parent d09e54aad1
commit f0764c6cfb
1 changed files with 3 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

7
koboldcpp.py
View file

@ -578,10 +578,9 @@ class ServerRequestHandler(http.server.SimpleHTTPRequestHandler):
if not kai_sse_stream_flag: if not kai_sse_stream_flag:
self.send_response(200) self.send_response(200)
self.end_headers() self.end_headers()
self.wfile.write(json.dumps(gen).encode()) self.wfile.write(json.dumps(gen).encode())
except: except:
print("Generate: The response could not be sent, maybe connection was terminated?") print("Generate: The response could not be sent, maybe connection was terminated?")
return return
finally: finally:
@ -647,7 +646,7 @@ def RunServerMultiThreaded(addr, port, embedded_kailite = None):
exitcounter = 999 exitcounter = 999
self.httpd.server_close() self.httpd.server_close()
numThreads = 6 numThreads = 8
threadArr = [] threadArr = []
for i in range(numThreads): for i in range(numThreads):
threadArr.append(Thread(i)) threadArr.append(Thread(i))