distributed▌

Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.

Distributed computing for larger-than-RAM pandas/NumPy workflows, enabling parallel processing and scalability across clusters.

Set up distributed tracing infrastructure with Jaeger or Zipkin to track requests across microservices and identify performance bottlenecks.

You are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools. Configure debugging workflows, implement tracing solutions, and establish troubleshooting practices for development and production environments.

Implement distributed tracing with Jaeger and Tempo for request flow visibility across microservices.

Track requests across microservices to identify latency, dependencies, and failure points. \n \n Supports Jaeger and Tempo backends with OpenTelemetry instrumentation for Python, Node.js, and Go \n Includes trace structure concepts (traces, spans, context, tags, logs) and automatic service dependency graph generation \n Provides sampling strategies (probabilistic, rate-limiting, adaptive) to control tracing overhead in production \n Covers context propagation via HTTP headers, trace analysis que