LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

Structured information extraction from documents

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

Layout Analysis Toolkit Yet Another Solution

A family of compressed models obtained via pruning and knowledge distillation

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

IOMMU IP compliant with the RISC-V IOMMU Specification v1.0

Chisel RISC-V Vector 1.0 Implementation

[TMLR 2024] Efficient Large Language Models: A Survey

百度贴吧水帖大全收集

Agentic components of the Llama Stack APIs

Backtest and live trading in Python

A list of alternatives for Adobe software

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

AL GAL是专门为Galgame场景设计的程序，旨在让得每一名用户都能享受到独一无二的剧情。程序基于renpy框架开发

Virtual whiteboard for sketching hand-drawn like diagrams

Algorithmic trading framework for cryptocurrencies.

The Autograd Engine

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

Cython QuantLib wrappers

🥰 Building AI-based conversational avatars lightning fast ⚡️💬

RoCE v2 hardware and software implementation

Plain C library for parsing AT commands for use in host devices.

MicroShell is a lightweight pure C implementation of shell emulator dedicated for embedded bare-metal systems.

An integrated CGRA design framework

An infrastructure for integrated EDA

EDA wiki

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Simple Byte pair Encoding mechanism used for tokenization process . written purely in C