https://pypi.org/project/llm-autotune/ Recent updates to the Python Package Index for llm-autotune en https://pypi.org/project/llm-autotune/0.1.1/ 39% faster TTFT, 67% less KV cache, zero config — autotune optimises local LLMs on Ollama, LM Studio, and MLX tanavc1@users.noreply.github.com Wed, 15 Apr 2026 07:29:22 GMT https://pypi.org/project/llm-autotune/0.1.0/ Automatic local-LLM inference configuration recommender for Ollama, LM Studio, and MLX tanavc1@users.noreply.github.com Wed, 15 Apr 2026 03:12:06 GMT