The story’s score and claims

Comments on No. 137 of 137 · vLLM Blog · edition of Friday 13 November 2026

Inkling 2 Small on vLLM: Day-0 Support

Summary

vLLM now supports Thinking Machines' Inkling 2 Small on day 0, a 594B-parameter (17B active) multimodal MoE model with 1M-token context. The release adds a native DSpark speculator, NVFP4/MXFP8 mixed-precision experts that allow single-node serving, and kernel and attention optimizations reaching up to 630 tokens/s per user at TP4, plus…

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules