makepad-shaders
Write custom GPU shaders and animations in Makepad using SDF drawing, uniforms, and the animator system. Use when creating visual effects, custom drawing, gradients, shadows, or animations in Makepad widgets.
gpu-cost-optimizer
Analyze GPU workloads and recommend optimal configurations. Get cost estimates, compare GPU options, avoid over-provisioning, and find the cheapest GPU that meets your requirements.
nemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
particles-router
Decision framework for particle system projects. Routes to specialized particle skills (gpu, physics, lifecycle) based on task requirements. Use when building particle effects or needing guidance on which particle techniques to combine.
particles-gpu
GPU-based particle systems using instanced rendering, buffer attributes, Points geometry, and custom shaders. Use when rendering thousands to millions of particles efficiently, creating particle effects like snow, rain, stars, or abstract visualizations.
arena-cli
>
