Pinned Loading

1. CoreLLM CoreLLM Public

   From-scratch multi-GPU LLM inference engine: paged KV cache, continuous batching, prefix caching, tensor parallelism, OpenAI-compatible server. Custom Triton kernels, vLLM-class throughput.

   Python 17 2

2. nano-browser-use nano-browser-use Public

   Browser Agent

   Python 2

3. slug-search slug-search Public

   Forked from OpenPipe/ART

   OpenPipe ART (Agent Reinforcement Trainer): train LLM agents

   Python 1

4. admire-finetuning-v2 admire-finetuning-v2 Public

   Python 1