WebLLM: high-performance in-browser LLM inference engine(github.com)130 points by saikatsg 1 month ago | 21 comments
MLC-LLM: GPT/Llama on consumer-class GPUs and phones(github.com)264 points by junrushao1994 3 years ago | 93 comments
LMQL: A query language for programming (large) language models(github.com)92 points by behnamoh 3 years ago | 10 comments
Show HN: Wd-40, a static webserver with automatic hot-reloads(github.com)99 points by baalimago 2 years ago | 74 comments