leosmerling Goto Github PK

followers: 1.0 following: 1.0 repos: 18.0 gists: 0.0

Name: Leo Smerling

Type: User

Bio: https://www.linkedin.com/in/leosmerling/

Location: Berlin

Leo Smerling's Projects

arrow-datafusion

Apache Arrow DataFusion and Ballista query engines

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

catboost_inference

Catboost inference examples in Rust and Python

feature-store

Machine Learning applications Feature Store implemented using hopeit.engine

fraud-poc

Fraud detection ML pipeline and serving POC using Dask and hopeit.engine. Project created with nbdev: https://www.fast.ai/2019/12/02/nbdev/

grpc-cache

gRPC server acting as read lock-free key-value store (Single writer multiple reader), to be used as a cache for features or service states that is updated externally.

grpc-streams

GRPC Event Streaming (i.e. lightweight in-memory Kafka replacement) server written in Rust

hopeit.engine

Python engine that allows creation and operations of reactive microservices

py-tonic

POC (for now) of a gRPC server made in Rust (based on Tonic+PYO3) to server Python code.

rust-bert

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

rust-tokenizers

Rust-tokenizer offers high-performance tokenizers for modern language models, including WordPiece, Byte-Pair Encoding (BPE) and Unigram (SentencePiece) models