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.
More from Infra
- Thinking Machines releases Inkling 2 Mini: 26B looped MoE with 3B active params, 1M context — mervenoyann · 2026-11-21
- Ollama CEO in Fortune: enterprise demand for open models keeps growing — ycombinator · 2026-11-21
- Nvidia plunges 13.17% in a single day to $126.75 — jfischoff · 2026-11-21
- vLLM ships Day-0 support for TML model, cuts GB200 decode latency to 3.84ms — vllm_project · 2026-11-21
- vLLM explains looped Inkling internals: shared weights with separate per-pass KV state — vllm_project · 2026-11-21
- Starcloud built a $2.5M space data center with the first H100 in orbit — chetanp · 2026-11-21