v0.4.1

[0.4.1] - 2025-06-03

🚀 New Features

✨ Pure Go Backend

• Run inference and fine-tuning, all from native Go!
• Added NewGoSession() backend, enabling Hugot to run in pure Go environments without C dependencies
• Implements our most requested community feature using SimpleGo from GoMLX
• Optimized for simpler workloads and environments where cgo is restricted
• Works best with smaller models like all-MiniLM-L6-v2
• Performance sweet spot: batches of approximately 32 inputs per call

📊 Performance Notes

• The Go backend currently performs 5-20x slower than C backends
• For performance-critical applications, we recommend using C backends (XLA or ORT)
• Significant speed improvements expected with the introduction of SIMD in Go 1.25

🐞 Known Limitations

• The Go backend and tokenizer currently lack support for certain operators
• If you encounter compatibility issues, please open an issue
• As a temporary workaround, use a C backend until the issue is resolved

🚨 Breaking Changes

• Build Tag Requirements Updated:
  • For NewORTSession(): Add -tags "ORT" or -tags "ALL" to your build arguments
  • For NewXLASession(): Add -tags "XLA" or -tags "ALL" to your build arguments

Added

• SimpleGo backend and SugarMe tokenizers for running Hugot without C dependencies

Changed

• Upgraded CUDA libraries to 12.9
• Upgraded GoMLX for performance improvements and bugfixes.