mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 06:10:29 +01:00
server : (tests) don't use thread for capturing stdout/stderr, bump openai client library (#10568)
* server : (tests) don't use thread for capturing stdout/stderr * test: bump openai to 1.55.2 * bump openai to 1.55.3
This commit is contained in:
parent
890719311b
commit
6c59567689
@ -2,6 +2,6 @@ aiohttp~=3.9.3
|
||||
pytest~=8.3.3
|
||||
huggingface_hub~=0.23.2
|
||||
numpy~=1.26.4
|
||||
openai~=1.30.3
|
||||
openai~=1.55.3
|
||||
prometheus-client~=0.20.0
|
||||
requests~=2.32.3
|
||||
|
@ -8,7 +8,6 @@ import os
|
||||
import re
|
||||
import json
|
||||
import sys
|
||||
import threading
|
||||
import requests
|
||||
import time
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
@ -161,26 +160,12 @@ class ServerProcess:
|
||||
self.process = subprocess.Popen(
|
||||
[str(arg) for arg in [server_path, *server_args]],
|
||||
creationflags=flags,
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE,
|
||||
stdout=sys.stdout,
|
||||
stderr=sys.stdout,
|
||||
env={**os.environ, "LLAMA_CACHE": "tmp"},
|
||||
)
|
||||
server_instances.add(self)
|
||||
|
||||
def server_log(in_stream, out_stream):
|
||||
for line in iter(in_stream.readline, b""):
|
||||
print(line.decode("utf-8"), end="", file=out_stream)
|
||||
|
||||
thread_stdout = threading.Thread(
|
||||
target=server_log, args=(self.process.stdout, sys.stdout), daemon=True
|
||||
)
|
||||
thread_stdout.start()
|
||||
|
||||
thread_stderr = threading.Thread(
|
||||
target=server_log, args=(self.process.stderr, sys.stderr), daemon=True
|
||||
)
|
||||
thread_stderr.start()
|
||||
|
||||
print(f"server pid={self.process.pid}, pytest pid={os.getpid()}")
|
||||
|
||||
# wait for server to start
|
||||
|
Loading…
Reference in New Issue
Block a user