Zijie-Tian

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

terraformer

CLI tool to generate terraform files from existing infrastructure (reverse Terraform). Infrastructure to Code

ZLUDA

CUDA on AMD GPUs

trax

Trax — Deep Learning with Clear Code and Speed

bypy

Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端

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.

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

script-commands

Script Commands let you tailor Raycast to your needs. Think of them as little productivity boosts throughout your day.

sd-scripts

AliceMind

ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

sparsegpt

Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

PiPPy

Pipeline Parallelism for PyTorch

llm-inference-benchmark

LLM Inference benchmark

local_llama

This repo is to showcase how you can run a model locally and offline, free of OpenAI dependencies.

ao

torchao: PyTorch Architecture Optimization (AO). Performant kernels that work with PyTorch.

reason

A shell for research papers

gdGPT

Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.

cuda_scheduling_examiner_mirror

A tool for examining GPU scheduling behavior.

Awesome-Resource-Efficient-LLM-Papers

a curated list of high-quality papers on resource-efficient LLMs 🌱

SparseFinetuning

Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry

structured_transposable_masks

Code for ICML 2021 submission

UnderstandingNLP

Natural Language Processing Analysis

frame

FRAME: Fast Roofline Analytical Modeling and Estimation

MLCarbon

End-to-end carbon footprint mod- eling tool

Opara

Opara is a lightweight and resource-aware DNN Operator parallel scheduling framework to accelerate the execution of DNN inference on GPUs.

model-evaluator

Evaluate Transformers from the Hub 🔥

wandbtocsv

CLI tool to export W&B metrics to a csv file.

lowtime

A time-cost tradeoff problem solver