infer

LLM Inference via Triton (Flexible & Modular): Focused on Kernel Optimization using CUBIN binaries, Starting from gpt-oss Model

multi_gpu_infer 多gpu预测 multiprocessing or subprocessing

Deterministic Data Driven Schema Modeling: Auto generate SQLalchemy models, cleaning and normalization functions from your csv files!

Fundamental files to train and evaluate a simple LSTM, MLP, CNN, and RNN model which can be trained on a time-series dataset composed of n input features and m outputs classes.

Create composable CLIs using shell args parser combinators and type hints

Automatically generate patch files for vulnerabilities detected by Infer Static Analyzer in C source code using LLM models.

Open standard for machine learning interoperability