Skip to content

[Klaud Cold][agentic experiment][Variant E] Kimi-K3 B200 agg TP8xPP2 agentic — direct vllm serve + SimpleCPU KV offload / Kimi-K3 B200 聚合式 TP8xPP2 智能体实验——直接 vllm serve + SimpleCPU KV 卸载 - #2370

Closed
functionstackx wants to merge 21 commits into
mainfrom
klaud/kimik3-b200-agentic-direct-vllm-simplecpu

fix: expandable_segments on the SimpleCPU-offload variant (prefill OOM)

b99c9ce
Select commit
Loading
Failed to load commit list.