v1.10.0

xorbitsai/inferencev1.10.0Sep 13, 2025by XprobeBot

AI Summary

This release introduces IP restriction functionality, Anthropic API format support, and enhanced JSON schema output for vLLM, along with various bug fixes.

Key Highlights

  • Added IP restriction via XINFERENCE_ALLOWED_IPS environment variable
  • Implemented Anthropic API format support
  • Enhanced OpenAI API support for vLLM JSON schema output

New Features

  • IP restriction by environment variable
  • Anthropic API format support
  • Enhanced vLLM JSON schema output
  • Kokoro-82M-v1.1-zh model support

Full Release Notes

# What's new in 1.10.0 (2025-09-13)
These are the changes in inference v1.10.0.
## New features
* FEAT: [model] Support Kokoro-82M-v1.1-zh by @JavisPeng in https://github.com/xorbitsai/inference/pull/4042
* FEAT: IP restriction by env: XINFERENCE_ALLOWED_IPS by @qxo in https://github.com/xorbitsai/inference/pull/4047
* FEAT: add support for the Anthropic API format by @OliverBryant in https://github.com/xorbitsai/inference/pull/4037
* FEAT: Openai API support vLLM json schema output by @OliverBryant in https://github.com/xorbitsai/inference/pull/4061
## Enhancements
* ENH: Update the environment dependencies for GOT-OCR2 by @Gmgge in https://github.com/xorbitsai/inference/pull/4031
* ENH: Clean memory during running MLX version's LLM models by @OliverBryant in https://github.com/xorbitsai/inference/pull/4026
* BLD: bump funasr to 1.2.7 by @leslie2046 in https://github.com/xorbitsai/inference/pull/4039
* BLD: cu128 version Dockerfile fix by @zwt-1234 in https://github.com/xorbitsai/inference/pull/4056
* BLD: Update Dockerfile.cu128 by @amumu96 in https://github.com/xorbitsai/inference/pull/4059
* REF: refactor tool calls functionality by @amumu96 in https://github.com/xorbitsai/inference/pull/4025
## Bug fixes
* BUG: Fix Kokoro-82M can't run on GPU by @OliverBryant in https://github.com/xorbitsai/inference/pull/4034
* BUG: [embeddings] fix parsing str type hf_overrides for vllm engine by @llyycchhee in https://github.com/xorbitsai/inference/pull/4052
* BUG: missing usage info in jina-embedding-v4 model response by @amumu96 in https://github.com/xorbitsai/inference/pull/4054
* BUG: distributed registration bug by @llyycchhee in https://github.com/xorbitsai/inference/pull/4046

## New Contributors
* @JavisPeng made their first contribution in https://github.com/xorbitsai/inference/pull/4042
* @qxo made their first contribution in https://github.com/xorbitsai/inference/pull/4047

**Full Changelog**: https://github.com/xorbitsai/inference/compare/v1.9.1...v1.10.0