KVCache.AI
@KVCache_AI
Hi, this is official account. We build systems for efficient LLM serving, including KTransformers, Mooncake and AgentENV.
가입 August 2018
109 팔로잉 중 1.1K 팬
Congratulations to the @lightseekorg TokenSpeed team! Great to see Kimi K3 optimizations running stably at production scale on GB300 and H200.
TokenSpeed × Kimi K3, Part I: TP8 optimization on GB300. Now stable 3+ weeks in production across ~1,000 B300 and ~2,000 H200 GPUs. Thanks @NVIDIAAI for engineering support and GB300 NVL72 access, and community teams for their support and contributions. 👇
더 보기
