●Change8

Migrating to vLLM v0.10.0rc2

Version v0.10.0rc2 introduces 1 breaking change. This guide details how to update your code.

Released: 7/24/2025

1
Breaking Changes
4
Migration Steps
9
Affected Symbols

⚠️ Check Your Code

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

AutoWeightsLoaderFreeKVCacheBlockQueueLogitsProcessorutils.current_streamQwen3CoderToolParserKVCacheTensorllm.chathf_processorDeepGemm

Breaking Changes

●Issue #1

Removed deprecated arguments in v0.10. Users must update their configuration to use current argument names.

Migration Steps

  1. 1
    Review and remove any v0.10 deprecated arguments from startup scripts or API calls.
  2. 2
    Update out-of-tree HPU plugins to align with new kv_cache_dtype handling.
  3. 3
    If using ROCm, ensure the latest build fixes are applied to avoid regressions.
  4. 4
    Update fp4 quantization calls to match the new API signature.

Release Summary

This release introduces VLM support via the transformers backend, enables shared-memory pipeline parallelism for CPUs, and adds support for NVIDIA SM100 (Blackwell) architectures. It also includes significant performance optimizations for MLA kernels and KV cache management alongside various bug fixes for distributed logging and ray integration.

Need More Details?

View the full release notes and all changes for vLLM v0.10.0rc2.

View Full Changelog