Research, software, data and methods. Inspect the context, compare your options, and take a useful next step.
Upstream project repository
Language-model serving engine for investigating batching, memory usage and decoding behavior under a fixed workload.
Investigate How does a fixed concurrency sweep affect latency and throughput while preserving declared generation settings?
Upstream project repository
Client tooling for experiment logging and artifact lineage, useful for studying what metadata a run actually records.
Investigate Can an explicitly offline run preserve a minimal parameter-and-metric manifest without transmitting research data?
Upstream project repository
Labeled multidimensional arrays and datasets for coordinate-aware scientific computation.
Investigate Does coordinate-aware arithmetic produce the expected intersection and values when coordinate labels differ?
Upstream project repository
Grid-aware operations for labeled arrays, including staggered grids used in geophysical models.
Investigate Do grid-aware differences reproduce a known linear field derivative with declared boundary conditions?
Upstream project repository
Deterministic and probabilistic verification metrics for labeled scientific arrays.
Investigate Do selected ensemble verification scores match explicit calculations with dimension weights and missing values?
Upstream project repository
Chunked multidimensional array storage with configurable stores and codecs.
Investigate Do different chunk layouts preserve dtype, shape, values, and fill-value semantics for a generated array?
Recorded license evidence is scoped to each source; it is not a blanket permission or a verification result.