vLLM v0.24.0 Adds MiniMax-M3 Support & BF16/FP8 Indexer

Core summary

One sentence to understand this update

vLLM v0.24.0 has been released, featuring significant contributions and adding 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 the MiniMax-M3 model and advanced quantization indexers, potentially enhancing performance and expanding model compatibility for their inference workflows.