biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Deprecation Warning when setting --engine-use-ray (#7424)

Browse Source 
Signed-off-by: Wallas Santos <wallashss@ibm.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: youkaichao <youkaichao@126.com>
This commit is contained in:
Wallas Henrique
2024-08-14 13:44:27 -03:00
committed by GitHub
parent 67d115db08
commit 70b746efcf
7 changed files with 56 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/async_engine/test_api_server.py
View File

@@ -1,3 +1,4 @@
import os
import subprocess
import sys
import time
@@ -35,11 +36,17 @@ def api_server(tokenizer_pool_size: int, engine_use_ray: bool,
"127.0.0.1", "--tokenizer-pool-size",
str(tokenizer_pool_size)
]
# Copy the environment variables and append `VLLM_ALLOW_ENGINE_USE_RAY=1`
# to prevent `--engine-use-ray` raises an exception due to it deprecation
env_vars = os.environ.copy()
env_vars["VLLM_ALLOW_ENGINE_USE_RAY"] = "1"
if engine_use_ray:
commands.append("--engine-use-ray")
if worker_use_ray:
commands.append("--worker-use-ray")
uvicorn_process = subprocess.Popen(commands)
uvicorn_process = subprocess.Popen(commands, env=env_vars)
yield
uvicorn_process.terminate()