●Change8

Migrating to vLLM v0.10.2

Version v0.10.2 introduces 4 breaking changes. This guide details how to update your code.

Released: 9/13/2025

4
Breaking Changes
4
Migration Steps
10
Affected Symbols

⚠️ Check Your Code

If you use any of these symbols, you need to read this guide:

torchflashinfermarlinNeuronBackendFlashMLAterratorchQwen2VLGLM-4.1VMamba1Whisper

Breaking Changes

●Issue #1

PyTorch 2.8.0 upgrade requires environment updates and may affect existing installations.

●Issue #2

FlashMLA is now disabled on NVIDIA Blackwell GPUs due to compatibility issues.

●Issue #3

Original Marlin quantization format has been removed.

●Issue #4

V0 Neuron backend and V0 pooling model support have been deprecated/removed.

Migration Steps

  1. 1
    Upgrade environment to support PyTorch 2.8.0.
  2. 2
    For aarch64, install via 'uv pip install vllm==0.10.2 --extra-index-url https://wheels.vllm.ai/0.10.2/ --torch-backend=auto'.
  3. 3
    Transition away from the original Marlin quantization format to supported alternatives.
  4. 4
    Update scripts using V0 Neuron or V0 pooling backends to use V1 or alternative implementations.

Release Summary

vLLM 0.10.2 introduces native aarch64 support, PyTorch 2.8.0 integration, and extensive optimizations for NVIDIA Blackwell GPUs. It expands model support to include Whisper and various vision-language models while maturing the V1 engine core.

Need More Details?

View the full release notes and all changes for vLLM v0.10.2.

View Full Changelog