sigpro

LLM101n

LLM101n: Let's build a Storyteller

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

lama

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

tiny-gpu

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

Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

MobileSAM

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

stable-diffusion.cpp

Stable Diffusion and Flux in pure C/C++

ZeroOmega

Manage and switch between multiple proxies quickly & easily.

Awesome-LLM-Compression

Awesome LLM compression research papers and tools.

LookOnceToHear

A novel human-interaction method for real-time speech extraction on headphones.

calculate-flops.pytorch

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)

T-MAC

Low-bit LLM inference on CPU with lookup table

MI-GAN

[ICCV 2023] MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices

sample-imageinpainting-HiFill

BitBLAS

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

ara

The PULP Ara is a 64-bit Vector Unit, compatible with the RISC-V Vector Extension Version 1.0, working as a coprocessor to CORE-V's CVA6 core

q-diffusion

[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.

LED

[ICCV 2023] Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising && [Arxiv 2023] Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model

I-BERT

[ICML'21 Oral] I-BERT: Integer-only BERT Quantization

Multispectral-Pedestrian-Detection-Resource

A list of resouces for multispectral pedestrian detection,including the datasets, methods, annotations and tools.

I-ViT

[ICCV 2023] I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference

lama-with-refiner

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

BitDistiller

[ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.

Fixed-Floating-Point-Adder-Multiplier

16-bit Adder Multiplier hardware on Digilent Basys 3

InspireFace

InspireFace is a cross-platform face recognition SDK developed in C/C++, supporting multiple operating systems and various backend types for inference, such as CPU, GPU, and NPU.

FEATHER

A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching

CSAPP

《深入理解计算机系统 第三版》家庭作业

SECDA

gamma-timeloop

IWAENC-2024-Informed-FastICA

Matlab implementations of algorithms and scripts of simulations presented in Informed FastICA: Semi-Blind Minimum Variance Distortionless Beamformer