michaelfeil Goto Github PK

academicpages

my personal website

autoawq

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.

bentoinfinity

candle

Minimalist ML framework for Rust

causalworld

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

commonroad_motionplaner_michaelf

Winning 2020 solution for the commonroad.io contest

ctranslate2

Fast inference engine for Transformer models

datachain

DataChain 🔗 Process and curate unstructured data using local ML models and LLM calls

deepembeddingapi

Enhancing privacy and security in Computer Vision by exposing Deep Learning Embeddings as API

deploy-weblink

Deploy your own weblink server to Heroku

ds-mobility-bike

dtu_mlops

embed

A stable, fast and easy-to-use inference library with a focus on a sync-to-async API

fastembed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

fauxpilot

FauxPilot - an open-source alternative to GitHub Copilot server

fl-in-healtcare-viz

Visualizations for the Seminar "Federated Learning in Healtcare"

flash-deberta

Deberta, but Flash

flash-fft-conv

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

foundation-model-stack

gpt-fast

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

gritlm

hf-hub-ctranslate2

Connecting Transformers on HuggingFace Hub with CTranslate2

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

infinity

Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip

iot_gateway_modbus

A MQTT Gateway connecting Modbus RTU and Google IoT Core

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

langchain

⚡ Building applications with LLMs through composability ⚡

litellm

Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs)

lm-evaluation-harness

A framework for few-shot evaluation of language models.

lstm-dlnn2020

Character-LSTM implementation in Numpy