#LLM serving26/10/2025
kvcached Unlocks Elastic KV Caching to Slash GPU Memory Waste for LLMs
kvcached provides a virtualized, elastic KV cache for LLM serving on shared GPUs, reducing memory waste and speeding activation across colocated models.
FILTER MODE ACTIVE
#LLM serving
Records found: 2
#LLM serving22/08/2025
CloudMatrix Supernode: Huawei's Peer-to-Peer Datacenter for Trillion-Scale LLMs
'Huawei's CloudMatrix builds a peer-to-peer supernode combining 384 Ascend 910C NPUs and 192 Kunpeng CPUs to deliver high-throughput, low-latency LLM serving, with CloudMatrix-Infer optimizing MoE and KV cache workloads.'