Beast code in Giters

d61h6k4's starred repositories

onnxruntime-genai

Generative AI extensions for onnxruntime

Language:C++MIT34000

speech_course

YSDA course in Speech Processing.

Language:Jupyter NotebookMIT18400

dla

Deep learning for audio processing

Language:Jupyter NotebookMIT54700

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Language:Jupyter NotebookNOASSERTION2318900

Olive

Olive is an easy-to-use hardware-aware model optimization tool that composes industry-leading techniques across model compression, optimization, and compilation.

Language:PythonMIT142200

lectures

Material for cuda-mode lectures

Language:Jupyter NotebookApache-2.0187700

FFmpeg

Mirror of https://git.ffmpeg.org/ffmpeg.git

Language:CNOASSERTION4393100

bazel

a fast, scalable, multi-language and extensible build system

Language:JavaApache-2.02276700

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonBSD-3-Clause537600

SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 languages, generated using PaLM 2 and summarize-then-ask prompting.

4200

ARES

Language:PythonApache-2.039300

ml-engineering

Machine Learning Engineering Open Book

Language:PythonCC-BY-SA-4.01027900

DOVER

[ICCV 2023, Official Code] for paper "Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives". Official Weights and Demos provided.

Language:Jupyter NotebookMIT23600

RecSysPapers

推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.

Language:PythonBSD-2-Clause115400

bytewax

Python Stream Processing

Language:PythonApache-2.0139800

raft

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

Language:CudaApache-2.069100

python-causality-handbook

Causal Inference for the Brave and True. A light-hearted yet rigorous approach to learning about impact estimation and causality.

Language:Jupyter NotebookMIT256700

river

🌊 Online machine learning in Python

Language:PythonBSD-3-Clause489800

Building-Low-Latency-Applications-with-CPP

Building Low Latency Applications with CPP by Packt Publishing

Language:HTMLMIT34200

applied-ml

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

MIT2683600

wasabi

🍣 A lightweight console printing and formatting toolkit

Language:PythonMIT44300

pyllms

Minimal Python library to connect to LLMs (OpenAI, Anthropic, AI21, Cohere, Aleph Alpha, HuggingfaceHub, Google PaLM2, with a built-in model performance benchmark.

Language:PythonMIT68700