●Change8

Migrating to vLLM v0.10.0rc1

Version v0.10.0rc1 introduces 1 breaking change. This guide details how to update your code.

Released: 7/20/2025

1
Breaking Changes
3
Migration Steps
7
Affected Symbols

⚠️ Check Your Code

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

ClassifierPoolerCompressedTensorsW8A8Fp8MoECutlassMethodFlexAttentionllm.chatfused_marlin_moeBatchedTritonExpertsDPEngineCoreActors

Breaking Changes

●Issue #1

Removal of V0 backends for CPU, XPU, and TPU. Users must transition to the V1 engine for these hardware platforms.

Migration Steps

  1. 1
    Upgrade to the V1 engine if using CPU, XPU, or TPU backends as V0 is no longer supported.
  2. 2
    Ensure the 'openai' python package meets the new minimum version requirements.
  3. 3
    Update custom model implementations to use the new 'use_cross_encoder' flag in ClassifierPooler if applicable.

Release Summary

This release introduces fp8 support for Triton experts, adds Llama 4 support, and migrates CPU/XPU/TPU backends exclusively to the V1 engine. It also includes significant performance optimizations for quantization kernels and initial support for the OpenAI Responses API.

Need More Details?

View the full release notes and all changes for vLLM v0.10.0rc1.

View Full Changelog