Ollama releases: v0.34.1

TL;DR

Ollama released version v0.34.1, addressing issues with ChatGPT model selector spacing and improving memory management by evicting cache snapshots and checking system free memory before loading new models, all while raising the token repeat limit to 100. These updates enhance stability and performance, making the software more reliable for users.

Detailed Summary

Ollama released version v0.34.1, which includes fixes for ChatGPT model selector spacing, improvements in managing memory usage by evicting prefix cache snapshots and waiting for available resources before loading new models, and an increase in the token repeat limit to 100 with error handling. These updates aim to enhance user experience and system efficiency in the application.

Key Points

• • app: fix ChatGPT model selector spacing
• • mlxrunner: Evict prefix cache snapshots from active conversation
• • mlxrunner: check system free memory, wait for evicted runners before loading next MLX model
• • llm: raise token repeat limit to 100 and return error instead