Results for “gpu-evaluation”

Evaluates RAG pipelines using a filesystem-based benchmark with corpus/ and train.json, running evaluate_rag.py to tune retrieval and generation flags and interpret RAGAS metrics.

Detect and validate GPU availability for MATLAB GPU computing. Use when the user can't use their GPU, or is setting up or selecting a GPU. Triggers on: gpuDevice, GPU setup, check GPU, GPU not found, GPU not working, can't use GPU, GPU not available, unable to find a supported GPU device, compatible GPU, canUseGPU, validateGPU.

Detects available CPU, GPU, memory, and disk resources and generates strategic recommendations for scientific computing tasks.

Diagnose frame-rate bottlenecks (CPU vs GPU bound FIRST), control Unreal Insights traces, sample live frame times, and annotate performance captures. Use when FPS is low/bad, the game is slow, or you need to find what is limiting the frame rate.

Honestly evaluate AI work quality using a two-axis scoring system with mandatory devil's advocate reasoning and cross-session anti-inflation detection.

Benchmarks a text-to-text transformer across GLUE, SuperGLUE, CNN/Daily Mail, SQuAD, and WMT, reporting GLUE average, BLEU, ROUGE-2-F, and Exact Match scores.

Build, optimize, backtest, rebalance, or analyze stock portfolios using NVIDIA-accelerated Mean-CVaR optimization with cuOpt GPU solver.

Reduces peak GPU memory in Megatron Bridge training by applying expandable segments, parallelism resizing, activation recompute, and CPU offloading constraints.

Diagnose and optimize slow-loading, high-memory, or low-FPS USD scenes using a structured workflow with profiling, validation, and mutation phases.

Diagnose and improve MSBuild project evaluation performance by analyzing phases, glob patterns, import chains, and property functions.

Optimize MATLAB design files for GPU Coder to generate faster CUDA code. Iteratively profiles, rewrites, and benchmarks until performance targets are met or diagnostics are resolved. Use when asked to: optimize for GPU Coder, improve GPU codegen performance, profile generated GPU/CUDA code, profile GPU MEX, fix gpuPerformanceAnalyzer diagnostics, speed up GPU MEX, reduce GPU memory transfers, improve kernel parallelism, rewrite MATLAB for CUDA, or run gpuPerformanceAnalyzer.

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, and other RAPIDS libraries for dramatic speedups on numerical, data, ML, graph, and simulation workloads.

KINTSUGI NOTEBOOK processing principles: Never sacrifice quality for speed, always use GPU when available. Trigger: performance optimization, CPU/GPU choice, fast mode, quality vs speed in NOTEBOOKS (not SLURM).

Systematically profile Node.js, Python, and Go applications to identify CPU, memory, and I/O bottlenecks, generate flamegraphs, analyze bundle sizes, optimize database queries, and run load tests with k6 and Artillery.

Performance regression detection using the browse daemon. (gstack)

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

Web browser game development principles. Framework selection, WebGPU, optimization, PWA.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

PC and console game development principles. Engine selection, platform features, optimization strategies.

GPU-accelerated correlation matrix computation with persistent SQLite caching to eliminate bottleneck at correlation calculation during symbol selection

Benchmarks inference latency and computational runtime of transformer models and MLX operations across Apple Silicon and NVIDIA GPU backends, with configurable input lengths and batch sizes.

`task-agent`/`review-agent`: use when CPU, memory, I/O, database, network, rendering, or cost needs measured bottleneck evidence; skip without a profiling need.

Performance Profiler

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

Analyzes game balance by extracting stats from code and running mathematical simulations, including DPS tier lists, TTK matrices, EHP comparisons, economy stress tests, progression pacing, and Monte Carlo RNG simulations.

Use when a bounded textual artifact (prompt, rubric, tool description, extraction instruction) keeps underperforming and success can be measured with an evaluator, dataset, or trace set. GEPA proposes evaluator-backed candidate rewrites through a normal PR/proposal adoption gate. Do not use for vague behavior changes, governance/persona/core-memory edits, fake metrics, or problems whose first honest task is defining the evaluator or collecting data.

GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.

Performs privilege escalation assessments on compromised Linux and Windows systems to identify paths from low-privilege access to root or SYSTEM-level control.

Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time". (gstack) Voice triggers (speech-to-text aliases): "speed test", "check performance".

通用跨模型审查：Review LLM 对任意研究制品进行独立评审，输出结构化评分、wiki 实体映射与改进建议

Use when profiling, diagnosing, or improving Three.js or WebGL game performance without regressing gameplay—frame-time drops, CPU/GPU pressure, draw calls, texture/geometry budgets, animation loops, adaptive quality, mobile performance, and browser performance verification.

Analyzes game AI systems in a codebase, covering behavior trees, finite state machines, GOAP, utility AI, pathfinding, steering, perception, difficulty adaptation, NPC dialogue, and AI debugging tools for Unity, Unreal, and Godot projects.

Evaluates computational throughput and real-time efficiency of embedded CPU and GPU platforms by measuring peak FLOPS via a matrix rotation kernel and assessing inference latency and power consumption on a robotic vision pipeline.