Change8

v0.22.1-rc0

📦 ollamaView on GitHub →
2 features🐛 2 fixes🔧 4 symbols

Summary

This release introduces model batching support and fixes several issues related to tokenization and desktop application startup behavior. It also includes support for NVIDIA TensorRT Model Optimizer import.

✨ New Features

  • Model support for batching has been added.
  • Support for NVIDIA TensorRT Model Optimizer import added to mlx backend.

🐛 Bug Fixes

  • Fixed multi-regex BPE offset handling in tokenizer.
  • Fixed desktop app startup killing active `ollama launch` sessions.

Affected Symbols