Story

vllm_blog ยท Nov 20, 2026 ยท news

Source brief

Inkling 2 Mini on vLLM: Day-0 Support for a Looped Model

vllm.aiNov 20, 2026
original source linked

In brief

vLLM supports Thinking Machines' Inkling 2 Mini from day 0: a looped MoE that runs its middle layers three times, with per-pass KV caches, gated messages between passes, fused kernels and DSpark speculative decoding.

Continue reading

Read the original at vllm.ai โ†’Open in live feed

Earlier in this thread 4 items