https://blog.lmcache.ai/2025-05-08-mooncake/

[giscus[bot]]

https://blog.lmcache.ai/2025-05-08-mooncake/

Overview of the Collaboration LMCache and Mooncake have announced a strategic collaboration aimed at pioneering a KVCache-centric Large Language Model (LLM) serving system. This partnership seeks to significantly enhance the efficiency, scalability, and responsiveness of LLM applications. By combining LMCache’s advanced KVCache management techniques with Mooncake’s powerful and optimized backend...

https://blog.lmcache.ai/2025-05-08-mooncake/

[prashant182]

For the model deployment, did you deploy a single model copy across all 8 GPUs or each GPU got one model copy? Also how many nodes did you use to test this feature? If GPUs are across different nodes i.e. 80 H100, (8 P5 instances) How does mooncake transfer KV Cache across instances?

[llc-kc]

what's you test code to give these data?