vLLM v0.33.0rc3 released
Key point
vLLM v0.33.0rc3, a high-throughput and memory-efficient inference and serving engine for LLMs, has been released.
vLLM v0.33.0rc3, a high-throughput and memory-efficient inference and serving engine for LLMs, has been released.
As a bugfix, this release includes pinning the ColUltraVBERT test checkpoint to the revision vL.
This item is a summary. The full, checkable version is at the original source:
Read the original at vLLM ↗