Ubicloud, which serves Kimi and DeepSeek models, scored its deployments on Moonshot AI's K2VV ToolCall benchmark, a 2,000-request test of whether generated tool calls match the tool's schema. Serving Kimi K2.6 on vLLM 0.28 returned the…
In the News: October 26, 2026 (Midday)
Ubicloud measured 92% tool-call schema accuracy serving Kimi K2.6 on vLLM, and 100% once constrained decoding was switched on.
Midday edition
Machine-readable
Download Markdown