cuopt-numerical-optimization-api

by NVIDIA3.6k

Developer Tools

LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.

Install

The skill file stays in the publisher's repository.

Paste the copied command in a terminal. It installs this SKILL.md into that agent.

npx skills add NVIDIA/skills --skill cuopt-numerical-optimization-api -a cursor -y

How do I install cuopt-numerical-optimization-api?: Download skills/cuopt-numerical-optimization-api/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does cuopt-numerical-optimization-api live?: The publisher keeps it at https://github.com/NVIDIA/skills.
Which agents can use cuopt-numerical-optimization-api?: Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.

Model and solve LP, MILP, and QP problems using NVIDIA cuOpt's GPU-accelerated solver.

Choose the reference for the user's interface:

Interface	When to use	Reference

Python	User is writing Python code	references/python_api.md
C / C++	User is embedding in a C/C++ application	references/c_api.md
CLI	User is solving from MPS files on the command line	references/cli_api.md

If the objective is...	And variables are...	Use
Linear (sum of `c_i * x_i`)	All continuous	LP
Linear	Some integer or binary	MILP
Has squared (`xx`) or cross (`xy`) terms	Continuous (integer QP not supported)	QP (beta)

Problem wording / concept	Variable type	Examples
Discrete entities (counts)	INTEGER	Workers, cars, trucks, machines, pilots, facilities, units to manufacture
Yes/no or on/off	INTEGER (binary, lb=0 ub=1)	Open a facility, run a machine, assign a person to a shift
Amounts that can be fractional	CONTINUOUS	Tonnes, litres, dollars, hours, kWh, proportion of capacity
Rates or fractions	CONTINUOUS	Utilization, percentage, share of budget

Problem	Likely cause	Fix
Infeasible	Conflicting constraints	Check constraint logic and bounds
Unbounded	Missing bounds	Add variable bounds
Slow solve	Large problem	Set time limit; increase gap tolerance
QP rejected with MAXIMIZE	QP only supports MINIMIZE	Negate the objective; negate the result
QP returns non-optimal	Q not PSD or badly scaled	Check Q is PSD; rescale variables

Setting	Purpose
`time_limit`	Stop after N seconds
`mip_relative_gap`	Stop MILP when within X% of optimal
`mip_absolute_tolerance`	Absolute MIP gap stop
`log_to_console`	Enable solver logging