xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 05:45:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix][Example] make lmcache v0 work. (#18051)

Browse Source 
Signed-off-by: Ma, Jianpeng <jianpeng.ma@intel.com>
This commit is contained in:
majianpeng 2025-05-14 14:43:44 +08:00 committed by GitHub
parent d4154c35a2
commit e7ef61c1f0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/lmcache/cpu_offload_lmcache.py
View File

@ -34,7 +34,7 @@ from vllm.config import KVTransferConfig
from vllm.engine.arg_utils import EngineArgs
def setup_environment_variables():
def setup_environment_variables(vllm_version: str):
# LMCache-related environment variables
# Use experimental features in LMCache
os.environ["LMCACHE_USE_EXPERIMENTAL"] = "True"
@ -44,6 +44,8 @@ def setup_environment_variables():
os.environ["LMCACHE_LOCAL_CPU"] = "True"
# Set local CPU memory limit to 5.0 GB
os.environ["LMCACHE_MAX_LOCAL_CPU_SIZE"] = "5.0"
if vllm_version == "v0":
os.environ["VLLM_USE_V1"] = "0"
@contextlib.contextmanager
@ -120,7 +122,7 @@ def main():
lmcache_connector = "LMCacheConnectorV1"
model = "meta-llama/Meta-Llama-3.1-8B-Instruct"
setup_environment_variables()
setup_environment_variables(args.version)
with build_llm_with_lmcache(lmcache_connector, model, args.version) as llm: