[Core][Bugfix][Perf] Introduce MQLLMEngine to avoid asyncio OH (#8157)

Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
This commit is contained in:
Alexander Matveev
2024-09-18 13:56:58 +00:00
committed by GitHub
co-authored by Nick Hill rshaw@neuralmagic.com <rshaw@neuralmagic.com> Robert Shaw Simon Mo
parent 9d104b5beb
commit 7c7714d856
36 changed files with 1464 additions and 1169 deletions
+7
View File
@@ -1,5 +1,12 @@
import os
from ..utils import compare_two_settings
# --enforce-eager on TPU causes graph compilation
# this times out default Health Check in the MQLLMEngine,
# so we set the timeout here to 30s
os.environ["VLLM_RPC_TIMEOUT"] = "30000"
def test_custom_dispatcher():
compare_two_settings("google/gemma-2b",