●Change8

Migrating to vLLM v0.9.1rc1

Version v0.9.1rc1 introduces 3 breaking changes. This guide details how to update your code.

Released: 6/9/2025

3
Breaking Changes
4
Migration Steps
9
Affected Symbols

⚠️ Check Your Code

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

LLMget_dummy_textget_dummy_mm_dataasync_timeoutPiecewiseCompileInterpreterAutoWeightsLoadervllm.bench.servetriton_unified_attentionpydantic.dataclasses

Breaking Changes

●Issue #1

Disallowed positional arguments other than 'model' when initializing the LLM class. Users must now use keyword arguments for all other parameters.

●Issue #2

Required overriding 'get_dummy_text' and 'get_dummy_mm_data' in model implementations, which may break custom model integrations that relied on base class defaults.

●Issue #3

Removed metrics that were deprecated in version 0.8, which may break monitoring dashboards or integrations relying on those specific keys.

Migration Steps

  1. 1
    Update LLM class initialization to use keyword arguments for all parameters except the model path.
  2. 2
    If using custom models, implement 'get_dummy_text' and 'get_dummy_mm_data' methods.
  3. 3
    Update monitoring systems to remove references to metrics deprecated in v0.8.
  4. 4
    Upgrade Pydantic if running on Python 3.10 to avoid compatibility errors.

Release Summary

This release introduces quantization and multi-LoRA support for Neuron/TPU, migrates configurations to Pydantic dataclasses, and enforces stricter keyword-only arguments for LLM initialization. It also includes significant bug fixes for MLA attention accuracy and V1 backend stability.

Need More Details?

View the full release notes and all changes for vLLM v0.9.1rc1.

View Full Changelog