Extending LMCache Remote Connectors: MooncakeStore as an Example
By LMCache Team and Tencent
-
-
Shaping NIXL-based PD Disaggregation in vLLM V1
By LMCache Team -
CacheBlend (Best Paper @ ACM EuroSys'25): Enabling 100% KV Cache Hit Rate in RAG
By LMCache Team
-
Open-Source LLM Inference Cluster Performing 10x FASTER than SOTA OSS Solution
By Production-Stack Team
-
AGI Infra for All: vLLM Production Stack as the Standard for Scalable vLLM Serving
By LMCache Lab