Speeding up LLM inference 2x times (possibly)
Here's a project I've been working on for the last few months.
Reactions (1)
Similar products
by description similarity
An educational Rust project for exporting and running inference on Qwen3 LLM family
A ~9M parameter LLM that talks like a small fish.
AutoThink
news.ycombinator.comBoosts local LLM performance with adaptive reasoning
Crespo
github.comTree-sitter AST blueprints instead of raw code for LLMs
A high-performance RDMA distributed file system for fast LLM Inference and GPU Training.