wailovet

LowMemoryBP

The official implementation of the paper "Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation"

cron

a cron library for go

Autofocus

Implementation of different autofocus functions using python. The main goal is to obtain efficiently the maximal contrast between pixels

CDAF

Contrast Detection Auto Focus

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

ao

PyTorch native quantization and sparsity for training and inference

x-flux

instant_id

AutoGGUF

automatically quant GGUF models

ComfyUI-GGUF

GGUF Quantization support for native ComfyUI models

jsonformer

A Bulletproof Way to Generate Structured JSON from Language Models

outlines

Structured Text Generation

ollama-copilot

Proxy that allows you to use ollama as a copilot like Github copilot

flash-attention

Fast and memory-efficient exact attention

flash-attention-2-builds

(Unofficial) Manual builds of wheels for https://github.com/Dao-AILab/flash-attention for Windows x64

SimpleTuner

A general fine-tuning kit geared toward diffusion models.

ComfyUI-AdvancedLivePortrait

Assets

alpaca_lora_4bit

SqueezeLLM

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

KVQuant

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

BlueLM

BlueLM(蓝心大模型): Open large language models developed by vivo AI Lab

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

AutoAWQ_kernels

torch-bnb-fp4

Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops

ppq

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

BitBLAS

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

optimum-quanto

A pytorch quantization backend for optimum

ComfyUI-AutomaticCFG

If your image was a pizza and the CFG the temperature of your oven: this is a thermostat that ensures it is always cooked like you want. Also adds a 30% speed increase. For ComfyUI / StableDiffusion

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.