ybai62868

AI-For-Beginners

12 Weeks, 24 Lessons, AI for All!

llm.c

LLM training in simple, raw C/CUDA

codellama

Inference code for CodeLlama models

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

tiny-gpu

A minimal GPU design in Verilog to learn how GPUs work from the ground up

lm-evaluation-harness

A framework for few-shot evaluation of language models.

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

matmulfreellm

Implementation for MatMul-free LM.

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

ThunderKittens

Tile primitives for speedy kernels

Time-LLM

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Triton-Puzzles

Puzzles for learning Triton

VITA

✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM

Nanoflow

A throughput-oriented high-performance serving framework for LLMs

depyf

depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.

fast-whisper-finetuning

basalt

A Machine Learning framework from scratch in Pure Mojo 🔥

timeloop

Timeloop performs modeling, mapping and code-generation for tensor algebra workloads on various accelerator architectures.

zero-bubble-pipeline-parallelism

Zero Bubble Pipeline Parallelism

xdsl

A Python Compiler Design Toolkit

vidur

A large-scale simulation framework for LLM inference

matmul.c

Fast multi-threaded matrix multiplication in C

triton-viz

cuda-tensorcore-hgemm

ParrotServe

[OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable

TiledKernel

TiledKernel is a code generation library based on macro kernels and memory hierarchy graph data structure.

sgemm_riscv

This project records the process of optimizing SGEMM (single-precision floating point General Matrix Multiplication) on the riscv platform.

rvv-kernels

RISCV Vector Kernel C/LLVM-IR generator

Ansor-AF-DS

This repository contains the figures, tables and source code in the ICS'24 paper: "Accelerated Auto-Tuning of GPU Kernels for Tensor Computations".