niits

openvino

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference

crawlee-python

Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.

GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

LivePortrait

Bring portraits to life!

generative-recommenders

Repository hosting code used to reproduce results in "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152, ICML'24).

lmquant

earthworm

Learning English through the method of constructing sentences with conjunctions

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

gs-quant

Python toolkit for quantitative finance

FlagGems

FlagGems is an operator library for large language models implemented in Triton Language.

path-to-senior-engineer-handbook

All the resources you need to get to Senior Engineer and beyond

k8s-dra-driver

Dynamic Resource Allocation (DRA) for NVIDIA GPUs in Kubernetes

lm-evaluation-harness

A framework for few-shot evaluation of language models.

enroot

A simple yet powerful tool to turn traditional container/OS images into unprivileged sandboxes.

MemGPT

Create LLM agents with long-term memory and custom tools 📚🦙

PiPPy

Pipeline Parallelism for PyTorch

following-instructions-human-feedback

onnx-mlir

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

granite-code-models

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

elasticsearch

Free and Open, Distributed, RESTful Search Engine

superset

Apache Superset is a Data Visualization and Data Exploration Platform

simple-evals

WorkArena

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

HAMi

Heterogeneous AI Computing Virtualization Middleware

grouped_gemm

PyTorch bindings for CUTLASS grouped GEMM.

qserve

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

mlops-zoomcamp

Free MLOps course from DataTalks.Club

cuda-kmeans

A novell, highly-optimized CUDA implementation of k-means algorithm.

windows

Windows inside a Docker container.

torchtune

A Native-PyTorch Library for LLM Fine-tuning