tengdecheng

tengdecheng's starred repositories

llm.c

LLM training in simple, raw C/CUDA

Language:CudaMIT16868 179 70

flash-attention

Fast and memory-efficient exact attention

Language:PythonBSD-3-Clause10759 104 780

cs231n.github.io

Public facing notes page

Language:Jupyter NotebookMIT9918 535 111

Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor

Language:PythonNOASSERTION9852 541 2680

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

Language:PythonMIT5379 46 920

openmlsys-zh

《Machine Learning Systems: Design and Implementation》- Chinese Version

Language:TeX3662 47 201

HIP

HIP: C++ Heterogeneous-Compute Interface for Portability

Language:C++MIT3447 141 825

riscv-isa-sim

Spike, a RISC-V ISA Simulator

Language:CNOASSERTION2187 132 765

SparseConvNet

Submanifold sparse convolutional networks

Language:C++NOASSERTION1992 44 222

TensorComprehensions

A domain specific language to express machine learning workloads.

Language:C++Apache-2.01754 108 176

spconv

Spatial Sparse Convolution Library

Language:PythonApache-2.01714 23 667

huggingface_hub

The official Python client for the Huggingface Hub.

Language:PythonApache-2.01669 59 790

hw

RTL, Cmodel, and testbench for NVDLA

Language:VerilogNOASSERTION1616 168 345

torch-mlir

The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

Language:C++NOASSERTION1173 247 606

SPIRV-Tools

Language:C++Apache-2.0997 84 1988

nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

Language:C++MIT919 44 204

Triton-Puzzles

Puzzles for learning Triton

Language:Jupyter NotebookApache-2.0626 3 6

mlir-tutorial

MLIR For Beginners tutorial

Language:C++538 12 14

pytensor

PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.

Language:PythonNOASSERTION244 12 300

NVTX

The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resources in your applications.

Language:CApache-2.0237 9 27