Uzha
Sign in
← Today's brief

Tools · Updated 15 Oct, 01:15 am IST

Ollama v0.40.5 updates MLX, Metal kernels and tool-call handling

Why it matters for readers: If you follow AI tooling, this shows ongoing improvements to performance and developer experience.

  • The release ports Metal custom kernels to CUDA.1
  • MLX received a version bump in this update.1
  • OpenAI-related code was changed to accept custom tool calls in Responses history.1
  • Documentation was updated for model recommendations and language standardization.1
  • The app clarifies cloud payment error messages and lists a new first-time contributor.1
SaveAsk about this story
Report a mistake in this summary

Get a brief like this every morning

Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.

Get started