vLLM v0.21.0rc1: PyTorch 2.11, HuggingFace Transformers v5, and Python 3.14 Support
vLLM published v0.21.0rc1 on May 12, 2026, advancing the baseline to PyTorch 2.11 and HuggingFace Transformers v5, and adding Python 3.14 to the supported versions. The RC follows the v0.20.2 patch (May 10) which stabilized DeepSeek V4 support and fixed KV block allocation errors in the V1 engine.
Why it matters
Pinning to Transformers v5 and PyTorch 2.11 aligns vLLM with the current upstream ecosystem, enabling new model architectures that depend on these versions.
Importance: 2/5
vLLM RC — PyTorch 2.11 + Transformers v5 baseline, ecosystem alignment
Sources
official
Releases · vllm-project/vllm