Loreon
Labs
Platform
Docs
Home
Ecosystems
Other
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
Other
Emerging
GitHub
Website
Stars
—
Forks
—
Contributors
8
Last push
2mo ago
Recent commits
Latest commits.
init storage manager after register kv caches (#2316)
83dfa16
chunxiaozheng
6mo ago
[Bugfix] Harden ZMQ proxy loop in `examples/disagg_prefill/disagg_proxy_server.py` (#2287)
d486410
tunglinwood
6mo ago
auto store remote to local pool (#2213)
6213f50
lisiG9
6mo ago
[Core] Introduce NixlStorageBackend dynamic mode (#2024)
1102e56
Tomer Shmilovich
6mo ago
[refactor] use shapes and dtypes in RemoteMetadata (#2315)
a641ed5
chunxiaozheng
6mo ago
[Controller] Use dealer mode for worker->Controller zmq communication (#2330)
0f2e110
maobaolong
6mo ago
Remove v0 surviving code (#2319)
842b1ec
maobaolong
6mo ago
Fix memory leak and circuit breaker in S3Connector batched_get (#2292)
2d80432
yangw
6mo ago
Top contributors
Builders behind this project.
YaoJiayi
143 commits
ApostaC
137 commits
maobaolong
134 commits
chunxiaozheng
80 commits
sammshen
70 commits
Shaoting-Feng
56 commits
hickeyma
54 commits
Siddhant-Ray
43 commits