KVCache.AI(@KVCache_AI):Huge congrats to the @vllm_project team on pushing DSpark training for Kimi-K3 to this scale! 🚀 As the high-performance data plane behind the disaggregated pipeline, Mooncake moves hidden states between vLLM inference and training workers, fully utilizing RDMA bandwidth with topology-aware routing and multi-NIC aggregation. A great example of Mooncake powering large-scale AI data movement beyond KV cache transfer. Read more:

2026.09.23 08:13

Huge congrats to the @vllm_project team on pushing DSpark training for Kimi-K3 to this scale! 🚀 As the high-performance data plane behind the disaggregated pipeline, Mooncake moves hidden states between vLLM inference and training workers, fully utilizing RDMA bandwidth with topology-aware routing and multi-NIC aggregation. A great example of Mooncake powering large-scale AI data movement beyond KV cache transfer. Read more:

Red Hat AI@RedHat_AI

2026.09.17 14:36

Kimi K3 is a 2.8T-parameter model. We trained a DSpark speculator for it, and the speedup holds up. Single-stream math reasoning goes from ~110 to ~435 tokens/sec per user. Under concurrent load, up to ~3.5x higher output throughput at matched interactivity. The drafter is a 5B model proposing 8 tokens a step, and on math it gets ~6.4 of them accepted per round. Training a drafter for a model this big meant going multi-node: Speculators plus a new Mooncake connector streaming hidden states between vLLM inference and training over RDMA. Two GB300 nodes to serve the target, one to train.