808 skills · sorted by relevance
Plan and create Google Kubernetes Engine clusters using templates for production, development, or AI workloads. Compare Google-managed and self-managed node options, review configurations before creation, and check settings for production readiness.
Manage isolated working environments in OpenShell using its command-line tool. Register gateways, create and connect to sandboxes, configure credential providers, and reuse workload templates with shared images, environment settings, and computing resources.
Improve MNN inference on OpenCL by measuring bottlenecks and refining GPU kernels, the code that performs calculations. The skill guides baseline measurements, correctness checks, Android device benchmarks, and integration of new OpenCL features with compatibility fallbacks.
Diagnose errors and incorrect inference results in MNN's QNN backend for Qualcomm HTP processors. Compare intermediate calculation data against CPU results to locate the first faulty operator, distinguish bugs from precision limits, and guide operator support and performance fixes.
Guides adapting OpenPI robot models to custom datasets and serving them to produce actions from observations. Covers JAX and PyTorch training, checkpoint conversion, and troubleshooting for normalization statistics and GPU memory.
Deploy language model APIs and run batch generation with vLLM. Configure GPU memory use, quantization—lower precision model storage—and distribution across GPUs, then test response times and monitor how many requests the server handles.
Guides fine-tuning and evaluation of OpenVLA-OFT robot models that turn images and language into actions. Covers LIBERO simulation, ALOHA deployment, LoRA adaptation that updates a small set of parameters, and troubleshooting action scaling or configuration mismatches.
Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.
Helps reduce GPU memory use by loading large language models in 4-bit or 8-bit formats, a technique called quantization. Covers bitsandbytes configuration, memory checks, QLoRA fine-tuning, and training with memory-saving optimizers.
Optimize transformer attention, the calculation that relates tokens to one another, using Flash Attention. The skill guides PyTorch integration, GPU memory reduction, performance measurement, and output comparisons for training or inference with long sequences.
Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.
Apply HQQ quantization, which stores language model weights using fewer bits without calibration examples. Covers precision settings, inference backends, saving compressed models, deployment with HuggingFace Transformers or vLLM, and further training with LoRA.
Implement Mamba, a model architecture that processes sequences through an internal state with computation scaling linearly with input length. Covers pretrained text generation, Mamba-1 and Mamba-2 configuration, speed comparisons with Transformers, and GPU memory troubleshooting.
Build data processing pipelines for machine learning, from preprocessing to batch predictions. Uses Ray Data to handle datasets larger than memory, distribute work across CPUs and GPUs, and feed data into training frameworks.
Estimate inference memory for models on Hugging Face Hub without downloading their weights. Check GPU capacity for Safetensors or GGUF files, with optional estimates for the KV cache, memory used to retain attention data during generation.
Audits GitHub Actions workflows that run AI coding agents. Traces how attacker-controlled content reaches prompts, checks permissions and sandbox settings, and reports evidence, severity, and fixes for prompt injection and related configuration risks.
Define a consistent process for unattended AI research using public sources. Limit clarification questions, show a search plan, distinguish facts from interpretations and assumptions, and keep reports structured so repeated investigations can be compared.
Plan competitive and market research across public news, financial records, statistics, patents, hiring, and operational signals. Separate observations from inferences and cross-check independent evidence to support market sizing, roadmap choices, pricing, and sales materials.
Compare batching, request scheduling, and memory management for a single model serving instance. Assess concurrent request capacity, response times, generation speed, and GPU time per result that meets the required quality and deadline.
Build chat, image generation, and speech transcription features on 0G Compute Network, a distributed GPU marketplace. This skill guides SDK integration, model fine-tuning, response processing for billing, and account funding through code patterns and CLI commands.
Run demanding scientific work on SSH compute hosts using direct execution or Slurm, a cluster job scheduler. Choose an enabled host, submit background jobs, check progress, collect outputs, and continue with analysis and artifact publication.
Fit regression and time series models in Python, then examine coefficients, uncertainty, and predictions. Check model assumptions, investigate unusual observations, and compare alternatives using detailed statistical summaries and diagnostic tests.
Develop Bayesian models for quantitative social science, from choosing priors to reporting posterior results. Guide MCMC, a sampling method for estimating distributions, check convergence, and assess sensitivity for hierarchical models and small datasets.
Choose and implement methods for estimating causal effects from observational data or policy changes. Guidance covers method assumptions, estimation, diagnostic checks, and robustness tests that examine whether findings hold under alternative analysis choices.