vLLM has released version 0.29.0rc1, which includes a bugfix for handling padded routes in CUTLASS MoE permutations. This release was tagged by khluu and includes contributions from Kevin Luu, Yongye Zhu, and Codex from OpenAI. AI
IMPACT Minor infrastructure update for an open-source LLM serving framework.
RANK_REASON This is a minor release (release candidate) of an open-source inference serving library, not a frontier model release or significant industry event.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →