Optimizes, profiles, and benchmarks CUDA, CUTLASS, Triton, and deep learning GPU workloads using evidence-driven profiling and ROI analysis.
Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF.
Builds a cult film recommendation agent with x402 payments.
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML.
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI).
Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install.
Install cuOpt — system and environment requirements only.
Developer installation — build cuOpt from source, run tests.
Install cuOpt for Python — pip, conda, Docker, verification.
LP, MILP, and QP (beta) with cuOpt — CLI only (MPS files, cuopt_cli).
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only.
cuOpt REST server — what it does and how requests flow.
Use when reviewing or refactoring code and wanting a structured lens beyond SOLID — applies Daniel Terhorst-North's CUPID properties to…
Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file…
Install and verify cuPyNumeric for Python — requirements, commands, verification.
Clean up, prune, and consolidate the lessons and memories stores — archive lessons that were never used, merge duplicates that say the…
Peer-Reviewer and portfolio-curator side of the TSI Shepherding Model — backlog stewardship, quarterly prioritization, funnel intake…
Conduct art historical research, provenance investigation, and scholarly analysis to inform exhibitions, acquisitions, and publications…
GitHub PR workflow automation including fetching unresolved comments, resolving review threads, and parallel comment resolution.
Automate Currents API tasks via Rube MCP (Composio).
Advanced Cursor Composer techniques: agent mode, parallel agents, complex