●Change8

Migrating to vLLM v0.10.1rc1

Version v0.10.1rc1 introduces 1 breaking change. This guide details how to update your code.

Released: 8/17/2025

1
Breaking Changes
2
Migration Steps
8
Affected Symbols

⚠️ Check Your Code

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

SpecializedManagerFusedMoEConfigDPEngineCoreActor._set_cuda_visible_devicesFlashInfer.MetadataBuilderNixlConnectorPhi3VImagePixelInputsGemma3.vision_embeddingsMamba2.RMSNorm

Breaking Changes

●Issue #1

The command line argument '--expand-tools-even-if-tool-choice-none' has been replaced with '--exclude-tools-when-tool-choice-none'. Users must update their startup scripts to use the new flag.

Migration Steps

  1. 1
    Update deployment scripts: replace '--expand-tools-even-if-tool-choice-none' with '--exclude-tools-when-tool-choice-none'.
  2. 2
    Upgrade flashinfer to v0.2.9rc1.

Release Summary

This release introduces model loader plugins, official Emu3 support, and significant performance optimizations for MoE kernels and FlashInfer. It also includes critical bug fixes for TPU, ROCm, and various quantization backends.

Need More Details?

View the full release notes and all changes for vLLM v0.10.1rc1.

View Full Changelog