7 projects
shad0wllm
Learns the fixed-choice decisions your LLM makes and answers the ones it is certified on in microseconds, from a small table on your CPU. Zero-code proxy for the OpenAI Decisions API, System One and chat models.
turboquantcpu
Near-optimal KV cache quantization for CPU LLM inference
lmfast
Democratized Small Language Model Training - Train, fine-tune, distill, and deploy sub-500M parameter models on Colab T4 in 30-40 minutes
blazemetrics
A high-performance NLP evaluation metrics library with a Rust core.
mcpconn
Simplified MCP client wrapper for efficient server interactions
plug-mcp
Simplified MCP client wrapper for efficient server interactions
open-mcp-protocol
An open-source Python package for MCP (Model Context Protocol)
