Hackernews posts about vLLM-MLX

1. vLLM-mlx – 65 tok/s LLM inference on Mac with tool calling and prompt caching (github.com)
   3 points by raullen 23 days ago | 1 comments
2. Show HN: Treni – single-binary GPU runtime for uncertainty-aware agents 5ms TTFT (treni-docs.pages.dev)
   2 points by andrewmonostate 27 days ago | 1 comments
3. vLLM-MLX – Run LLMs on Mac at 464 tok/s (github.com)
   33 points by waybarrios 2 months ago | 3 comments
4. Launch HN: Cactus (YC S25) – AI inference on smartphones (github.com)
   123 points by HenryNdubuaku 6 months ago | 63 comments
5. Show HN: Python SDK for RamaLama AI Containers (github.com)
   1 points by ersatz_username about 2 months ago | discuss
6. Trying VLLM Ideas on Apple Silicon with MLX (WIP) (github.com)
   2 points by waybarrios 3 months ago | 1 comments
7. Run LLMs on macOS using LLM-mlx and Apple's MLX framework (simonwillison.net)
   6 points by simonw about 1 year ago | discuss
8. The insecure evangelism of LLM maximalists (lewiscampbell.tech)
   251 points by todsacerdoti 2 months ago | 280 comments
9. Against LLM Maximalism (explosion.ai)
   1 points by softwaredoug 9 months ago | discuss
10. Show HN: Built a free moderation API after failing to find one (the-profanity-api.com)
    3 points by Olehype about 1 month ago | discuss
11. Show HN: Cai – The fastest CLI tool for prompting LLMs (github.com)
    1 points by adius almost 2 years ago | discuss