michaelfeil

CNC_Machining

data set for process monitoring on CNC machines

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

candle-flash-attn-v3

cognita

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

commonroad_motionplaner_michaelf

Winning 2020 solution for the commonroad.io contest

embed

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

hf-hub-ctranslate2

Connecting Transformers on HuggingFace Hub with CTranslate2

infinity

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

iot_gateway_modbus

A MQTT Gateway connecting Modbus RTU and Google IoT Core

skyjo_rl

Multi-Agent Reinforcement Learning Environment for the card game SkyJo, compatible with PettingZoo and RLLIB

michaelfeil/infinity

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

michaelfeil/embed

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

michaelfeil/hf-hub-ctranslate2

Connecting Transformers on HuggingFace Hub with CTranslate2

michaelfeil/skyjo_rl

Multi-Agent Reinforcement Learning Environment for the card game SkyJo, compatible with PettingZoo and RLLIB

michaelfeil/candle-flash-attn-v3

michaelfeil/bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

michaelfeil/cognita

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

michaelfeil/flash-deberta

Deberta, but Flash

michaelfeil/llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

michaelfeil/academicpages

my personal website

michaelfeil/BentoInfinity

michaelfeil/candle

Minimalist ML framework for Rust

michaelfeil/candle-cublaslt

michaelfeil/datachain

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

michaelfeil/fastembed

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

michaelfeil/hf_transfer

michaelfeil/JamAIBase

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

michaelfeil/kubeai

Private Open AI on Kubernetes

michaelfeil/pylabrobot

An interactive & hardware agnostic interface for lab automation

michaelfeil/qdrant

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

michaelfeil/qdrant-client

Python client for Qdrant vector search engine

michaelfeil/samba-qa

Production RAG Based on API Controllers

michaelfeil/sglang

SGLang is a fast serving framework for large language models and vision language models.

michaelfeil/start-rag

michaelfeil/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.

michaelfeil/TensorRT-Model-Optimizer

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.

michaelfeil/text-embeddings-inference

A blazing fast inference solution for text embeddings models

michaelfeil/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

michaelfeil/triton

Development repository for the Triton language and compiler

michaelfeil/zerox

Zero shot pdf OCR with gpt-4o-mini