vLLM v0.24.0 Release: Adds MiniMax-M3 Model Support and BF16/FP8 Indexer

Core summary

One sentence to understand this update

vLLM v0.24.0 has been released, featuring 571 commits, and notably adds support for the new MiniMax-M3 model along with a BF16/FP8 indexer.

Impact & opportunity

What this could mean

Builders using vLLM can now leverage MiniMax-M3 for their applications and benefit from potential performance gains with BF16/FP8 indexing.