Hackernews posts about vLLM-MLX

RSS feed for vLLM-MLX

01
newvLLM-MLX – Run LLMs on Mac at 464 tok/sgithub.com
▲ 33waybarrios 295d 💬 3
02
newvLLM-mlx – 65 tok/s LLM inference on Mac with tool calling and prompt cachinggithub.com
▲ 3raullen 254d 💬 1
03
newLaunch HN: Cactus (YC S25) – AI inference on smartphonesgithub.com
▲ 123HenryNdubuaku 414d 💬 63
04
newShow HN: Python SDK for RamaLama AI Containersgithub.com
▲ 1ersatz_username 284d discuss
05
newTrying VLLM Ideas on Apple Silicon with MLX (WIP)github.com
▲ 2waybarrios 335d 💬 1
06
newShow HN: Treni – single-binary GPU runtime for uncertainty-aware agents 5ms TTFTtreni-docs.pages.dev
▲ 2andrewmonostate 257d 💬 1
07
newRun LLMs on macOS using LLM-mlx and Apple's MLX frameworksimonwillison.net
▲ 6simonw 629d discuss
08
newThe insecure evangelism of LLM maximalistslewiscampbell.tech
▲ 251todsacerdoti 297d 💬 280
09
newAgainst LLM Maximalismexplosion.ai
▲ 1softwaredoug 509d discuss
10
newShow HN: Browser Harness – Gives LLM freedom to complete any browser taskgithub.com
▲ 134gregpr07 196d 💬 66
11
newCan you help reconcile my first/second-hand LLM Experience with HN's Experience?
▲ 5didigamma 179d 💬 7
12
newShow HN: Built a free moderation API after failing to find onethe-profanity-api.com
▲ 3Olehype 273d discuss