vLLM 0.33.0 adds new models and CUDA 13.0-only builds
vLLM released version 0.33.0 with 927 commits from 389 contributors, including 122 new contributors. The release adds support for models such as Reflection Beam-1.0, AliceAI-Foundation-80B-A3B, Recursive Flint, Step-5 Preview, Alpamayo 2 Super, Nemotron Parse 3.5 and MiniCPM-OCR 1.0, while upgrading to PyTorch 2.14.0. It also introduces speculative-decoding changes and publishes release artifacts for CUDA 13.0 only; project benchmarks cited in the release notes report throughput gains, but no independent measurements are provided.
This major vLLM update expands model coverage and serving capabilities, but users requiring CUDA 12.9 artifacts must switch to the release's CUDA 13.0 builds.
The source text is unavailable here. Read the original for the full story.
#vLLM 0.33.0#PyTorch#CUDA#Reflection Beam-1.0#AliceAI-Foundation-80B-A3B#Recursive Flint#Step-5 Preview#NVIDIA Alpamayo 2 Super#Nemotron Parse 3.5#MiniCPM-OCR 1.0#DeepSeek-V4.1-Flash#DSpark