Inference RWKV v5, v6 and (WIP) v7 with Qualcomm AI Engine Direct SDK

💥 Blazing fast terminal file manager written in Rust, based on async I/O.

Fast OS-level support for GPU checkpoint and restore

Open-source Framework for HPCA2024 paper: Gemini: Mapping and Architecture Co-exploration for Large-scale DNN Chiplet Accelerators

how to optimize some algorithm in cuda.

Fast Multimodal LLM on Mobile Devices

Puzzles for learning Triton, play it with minimal environment configuration!

Puzzles for learning Triton

A Chinese (Simplified) Translation Project for the Create: Astral modpack.

General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for…

A tool for bandwidth measurements on NVIDIA GPUs.

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

Low-bit LLM inference on CPU with lookup table

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

LLM inference in C/C++

A Pascal to C/RISC-V compiler based on YACC

Code for Diversity-Enhanced Learning for Instruction Adaptation in Large Language Models

Linux-capable out-of-order superscaler multicore LoongArch32 (LA32 / LA32R) processor.

Dynamic Memory Management for Serving LLMs without PagedAttention

llama3 implementation one matrix multiplication at a time

夏令营截止日期DDL静态网页

Open-source training data and evaluation tools used in Token-Efficient Leverage Learning

My personal vim/neovim configuration files, dotfiles, docs and other scripts.

A tool to decode RISC-V and LoongArch and MIPS instructions in gtkwave

A tool to decode RISC-V and LoongArch instructions in gtkwave

适用于龙芯杯团队赛入门选手的应急cache模块