Stars
My attempt at implementing retreival augmented generation on Ollama and other LLM services using chromadb and langchain while also providing an easy to understand, clean code for others since nobod…
Exocompilation for productive programming of hardware accelerators
Efficient C++ implementation of the Cassowary constraint solving algorithm
🍕 Peer-to-peer file transfers in your browser
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
Model swapping for llama.cpp (or any local OpenAPI compatible server)
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Simple to install, powerful command-line based AI agent system for coding.
Convert downloaded Ollama models back into their GGUF equivalent format
🖥️ A small, customizable and extensible MCU-class 32-bit RISC-V soft-core CPU and microcontroller-like SoC written in platform-independent VHDL.
An open-source microcontroller system based on RISC-V
yosys, nextpnr, apicula and openFPGALoader in vscode using OSS-CAD-Suite
Examples for the Lushay Labs tang nano 9k series
Par (⅋) is an experimental concurrent programming language. It's an attempt to bring the expressive power of linear logic into practice.
A minimal-area RISC-V core with a scalable data path to 1, 2, 4, or 8 bits and manifold variants.
Force DeepSeek r1 models to think for as long as you wish
Use LLM to generate and execute commands in your shell
Framework for building conversational agents using a Finite State Machine (FSM) and LLMs
Blazingly fast, modern C++ API using coroutines for efficient RTL verification and co-simulation via the VPI interface