vLLM ships day-0 support for Thinking Machines' new looped Inkling model

vllm_project · x · 2026-11-21

vLLM announced day-0 support for Thinking Machines' newly released looped Inkling model: 12 shared core layers, 3 passes per token, with gated messages passed from one pass to the next.

The integration marks a fast adaptation to this new model paradigm; follow-up posts in the thread detail kernel-count and latency optimizations on GB200.

Original post →

More from Infra

Infra channel →