Back to AI intel
重点
vLLM v0.30.0 Released with DeepSeek-V4.1-Flash Support
AI intel briefing
Core summary
One sentence to understand this update
vLLM v0.30.0 has been released, featuring 762 commits and adding support for new models like DeepSeek-V4.1-Flash, which stores the entire KV in MXFP8.
Impact & opportunity
What this could mean
Builders can leverage vLLM's updated performance and support for new models like DeepSeek-V4.1-Flash to enhance their LLM deployment efficiency.
Source
View original