Stars
OrcaLoca: An LLM Agent Framework for Software Issue Localization [ICML 25]
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
Visualizer for neural network, deep learning and machine learning models
Compilation of useful documents and scientific papers about Blockchain & cryptocurrencies.
Apache Heron (Incubating) is a realtime, distributed, fault-tolerant stream processing engine from Twitter
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
cache-friendly multithread matrix factorization
Graph-algorithm inferences over local groundings of first-order logic programs
OpenCL library to train deep convolutional neural networks