Model and solve linear, mixed-integer, and quadratic programming problems using GPU-accelerated solvers via Python, C, or CLI.
- GitHub stars
- 3,934
- Files
- 52
- Last commit
- Nov 11, 2026
- License
- Apache-2.0
- Allowed tools
- —
What does the cuopt-numerical-optimization-api skill do?
cuopt-numerical-optimization-api is an agent skill. Model and solve linear, mixed-integer, and quadratic programming problems using GPU-accelerated solvers via Python, C, or CLI.
Summary generated from the skill's SKILL.md.
About the cuopt-numerical-optimization-api skill
Solving linear, mixed-integer, and quadratic programming problems using GPU acceleration is what this skill enables for developers and researchers. It provides access to the NVIDIA cuOpt solver through Python, C/C++, or a command line interface. An agent should load this tool when a user needs to model complex mathematical optimizations, such as determining resource flows or making discrete yes/no decisions.
Beyond direct API calls, the skill acts as a backend for established modeling languages including AMPL, GAMS, PuLP, JuMP, Pyomo, and CVXPY. This allows users to switch to GPU-accelerated solving with minimal code changes. The tool handles continuous variables for linear problems and integer variables for discrete counts or binary choices. It also supports quadratic programming in beta for minimizing variance or squared errors, though it requires the objective to be a minimization task and the matrix to be positive semi-definite.
What an agent can do with it
- 1Solve continuous resource allocationDetermine the optimal distribution of fractional amounts like liters or dollars using linear programming.
- 2Manage discrete entity countsCalculate the number of trucks or workers needed for a specific task using mixed-integer programming.
- 3Minimize variance in portfoliosPerform quadratic programming to minimize squared error or variance in a dataset.
- 4Integrate with existing modelsUse cuOpt as a solver backend for a model already written in Pyomo or CVXPY.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the cuopt-numerical-optimization-api skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the cuopt-numerical-optimization-api skill in Claude Code
~/.claude/skills/cuopt-numerical-optimization-api/SKILL.md
$ npx degit NVIDIA/skills/skills/cuopt-numerical-optimization-api ~/.claude/skills/cuopt-numerical-optimization-apiInstall the cuopt-numerical-optimization-api skill in Claude Code (project)
.claude/skills/cuopt-numerical-optimization-api/SKILL.md
$ npx degit NVIDIA/skills/skills/cuopt-numerical-optimization-api .claude/skills/cuopt-numerical-optimization-apiInstall the cuopt-numerical-optimization-api skill in Codex
~/.agents/skills/cuopt-numerical-optimization-api/SKILL.md
$ npx degit NVIDIA/skills/skills/cuopt-numerical-optimization-api ~/.agents/skills/cuopt-numerical-optimization-apiInstall the cuopt-numerical-optimization-api skill in Gemini CLI
~/.gemini/skills/cuopt-numerical-optimization-api/SKILL.md
$ npx degit NVIDIA/skills/skills/cuopt-numerical-optimization-api ~/.gemini/skills/cuopt-numerical-optimization-apiInstall the cuopt-numerical-optimization-api skill in Claude.ai
npx degit NVIDIA/skills/skills/cuopt-numerical-optimization-api cuopt-numerical-optimization-api && zip -r cuopt-numerical-optimization-api.zip cuopt-numerical-optimization-api # claude.ai → Customize → Skills → + → Create skill → Upload a skill → cuopt-numerical-optimization-api.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachablenvidia/skills/skills/cuopt-numerical-optimization-api is public and reachablegithub.com/nvidia/skills/tree/HEAD/skills/cuopt-numerical-op ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/nvidia/skills/commits ↗Pass
- No download-and-run or credential theft in scripts5 of 10 scripts read; none of them downloads and runs code, the rest were not readFinding
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/nvidia/skills/blob/HEAD/skills/cuopt-numerical-op ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/nvidia/skills/blob/HEAD/skills/cuopt-numerical-op ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 104 linesgithub.com/nvidia/skills/blob/HEAD/skills/cuopt-numerical-op ↗Pass
SKILL.md
View on GitHubcuOpt Numerical Optimization API
Model and solve LP, MILP, and QP problems using NVIDIA cuOpt's GPU-accelerated solver.
Interface Selection
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 interface is not yet clear, ask before writing any code.
Already using a modeling language? cuOpt also works as a solver backend for third-party modeling tools — AMPL, GAMS / GAMSPy, PuLP, JuMP, Pyomo, and CVXPY — with near-zero code changes (point the model's solver at cuOpt). CVXPY additionally covers convex QP and, in beta, QCQP / SOCP. Prefer this when the user already has a model in one of these tools rather than porting it to the cuOpt API. See Third-Party Modeling Languages.
Choosing LP vs MILP vs QP
Decide from the objective and variables:
| 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 (x*x) or cross (x*y) terms |
Continuous (integer QP not supported) | QP (beta) |
Prefer LP when the problem allows it. LP solves faster and has stronger optimality guarantees. Use MILP only when the problem logically requires whole numbers or yes/no decisions. Use QP only when the objective is genuinely quadratic (variance, squared error, kinetic energy).
- Use LP when every quantity can meaningfully be fractional: flows, proportions, rates, dollars, hours, tonnes of material, etc.
- Use MILP when the problem mentions counts of discrete entities, yes/no choices, or either/or decisions (e.g. open a facility or not, assign a person to a shift, number of trucks).
- Use QP when the objective minimizes variance, squared error, or any expression with
x*xorx*yterms (portfolio optimization, least squares, regularized regression).
Integer vs Continuous from Wording
| 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 |
Rule of thumb: "How many things" → INTEGER. "How much" → CONTINUOUS.
QP Rules (all interfaces)
- MINIMIZE only — the solver rejects MAXIMIZE for quadratic objectives. To maximize
f(x), minimize-f(x)and negate the reported objective value. - Continuous variables only — integer QP is not supported.
- Q should be positive semi-definite for a convex, well-posed problem.
- Beta — API may evolve; treat as production-capable for typical convex QP.
Dual Values
Duals and reduced costs are available for LP and QP only:
- MILP — no duals (integer optima are not continuous).
- Quadratic constraints — duals unavailable even for LP/QP; all values return
NaN. - PDLP warmstart — LP only; MILP solves do not accept a PDLP warmstart.
Common Issues (all interfaces)
| 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 |
Solver Settings (concepts)
| 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 |
Syntax varies by interface — see the interface reference file.
Files in this skill
52cuopt-numerical-optimization-api skill questions
How do I install the cuopt-numerical-optimization-api skill in Claude Code?
Run npx degit NVIDIA/skills/skills/cuopt-numerical-optimization-api ~/.claude/skills/cuopt-numerical-optimization-api. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the cuopt-numerical-optimization-api skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
Can I use cuOpt with existing modeling languages like Pyomo or PuLP?
Yes, cuOpt works as a solver backend for third-party tools including AMPL, GAMS, PuLP, JuMP, Pyomo, and CVXPY.