xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 16:05:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Update the example code, make it work with the latest lmcache (#19453)

Browse Source 
Signed-off-by: Runzhen Wang <wangrunzhen@gmail.com>
This commit is contained in:
runzhen 2025-06-11 05:42:20 -07:00 committed by GitHub
parent 5c8d34a42c
commit 943ffa5703
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/others/lmcache/cpu_offload_lmcache.py
View File

@ -28,8 +28,8 @@ import os
import time
from dataclasses import asdict
from lmcache.experimental.cache_engine import LMCacheEngineBuilder
from lmcache.integration.vllm.utils import ENGINE_NAME
from lmcache.v1.cache_engine import LMCacheEngineBuilder
from vllm import LLM, SamplingParams
from vllm.config import KVTransferConfig

4
examples/others/lmcache/kv_cache_sharing_lmcache_v1.py
View File

@ -17,8 +17,8 @@ import subprocess
import time
from multiprocessing import Event, Process
from lmcache.experimental.cache_engine import LMCacheEngineBuilder
from lmcache.integration.vllm.utils import ENGINE_NAME
from lmcache.v1.cache_engine import LMCacheEngineBuilder
from vllm import LLM, SamplingParams
from vllm.config import KVTransferConfig
@ -105,7 +105,7 @@ def run_retrieve(store_done, prompts, timeout=1):
def run_lmcache_server(port):
server_proc = subprocess.Popen(
["python", "-m", "lmcache.experimental.server", "localhost", str(port)]
["python", "-m", "lmcache.v1.server", "localhost", str(port)]
)
return server_proc