diff --git a/examples/others/lmcache/cpu_offload_lmcache.py b/examples/others/lmcache/cpu_offload_lmcache.py index 354e4cc8c5723..9138b53679b3f 100644 --- a/examples/others/lmcache/cpu_offload_lmcache.py +++ b/examples/others/lmcache/cpu_offload_lmcache.py @@ -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 diff --git a/examples/others/lmcache/kv_cache_sharing_lmcache_v1.py b/examples/others/lmcache/kv_cache_sharing_lmcache_v1.py index 508cf4a5a4987..46e2d903d4be0 100644 --- a/examples/others/lmcache/kv_cache_sharing_lmcache_v1.py +++ b/examples/others/lmcache/kv_cache_sharing_lmcache_v1.py @@ -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