An index of datasets, SDKs, APIs and other open source code created by Microsoft researchers and shared with the broader academic community. We also maintain a collection highlighting some of the tools you’ll find here.
Trace is a new AutoDiff-like tool for training AI systems end-to-end with general feedback (like numerical rewards or losses, natural language text, compiler errors, etc.). Trace generalizes the back-propagation algorithm by capturing and propagating an…
LongRoPE is a novel method that extends the context window of pre-trained LLMs to an impressive 2048k tokens by non-uniformly rescaling RoPE positional embeddings. LongRoPE has been integrated into Microsoft Phi-3.
A public framework for time-series forecasting with spiking neural networks (SNNs).
The Intelligence Toolkit is a suite of interactive workflows for creating AI intelligence reports from real-world data sources. The toolkit is designed to help users identify patterns, answers, relationships, and risks within complex datasets, with…
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
MetaOpt is the first general-purpose and scalable tool that enables users to analyze a broad class of heuristics through easy-to-use abstractions that apply to a broad range of practical heuristics. For more information, checkout MetaOpt’s project webpage and…
VisEval: A NL2VIS Benchmark. VisEval is a benchmark designed to evaluate visualization generation methods. In this repository, we provide both the toolkit to support the benchmarking, as well as the data used for benchmarks.
Microsoft MicroCode is an icon-based programming language and editor for young learners to code with the BBC micro:bit V2. MicroCode allows you to program the micro:bit V2 with only an Arcade shield accessory – no…
A dataset of social artifacts from different Indian geographical subcultures. This repo hosts the code to run experiments on the DOSA dataset.
TE-CCL is a tool to generate collective communication schedules for large topologies using a Traffic Engineering-based solver. TE-CCL takes in a topology and collective (e.g. AllGather) and outputs a schedule (in JSON) detailing data transfer…
