Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA (github.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of github.com: Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA

First screen, captured 4 months ago.

Looks similar

Screenshot of github.com: Show HN: Find the best local LLM for your hardware, ranked by benchmarks

Show HN: Find the best local LLM for your hardware, ranked by benchmarks (github.com)

268 points by andyyyy64 5 months ago | 62 comments

Screenshot of github.com: Show HN: Yet another memory system for LLMs

Show HN: Yet another memory system for LLMs (github.com)

144 points by blackmanta 1 year ago | 38 comments

Screenshot of github.com: Show HN: Talos – Open-source WASM interpreter for Lean

Show HN: Talos – Open-source WASM interpreter for Lean (github.com)

78 points by mfornet 4 months ago | 20 comments

Screenshot of github.com: Show HN: We made our own inference engine for Apple Silicon

Show HN: We made our own inference engine for Apple Silicon (github.com)

145 points by darkolorin 1 year ago | 42 comments

Screenshot of github.com: Tilck: A tiny Linux-compatible kernel

Tilck: A tiny Linux-compatible kernel (github.com)

277 points by chubot 1 year ago | 53 comments

Screenshot of github.com: Tini: A tiny but valid `init` for containers

Tini: A tiny but valid `init` for containers (github.com)

9 points by thunderbong 1 year ago | 0 comments