Results for “inference”

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.

The English summary is being prepared. Showing the original description.

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.

The English summary is being prepared. Showing the original description.

Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.

The English summary is being prepared. Showing the original description.

Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.

The English summary is being prepared. Showing the original description.

NVIDIA DeepStream SDK development guidance for Python pyservicemaker pipelines, video analytics, TensorRT integration, and streaming inference workflows.

The English summary is being prepared. Showing the original description.

Reverse-engineer why a design decision was made. Move from observation to inference. Use when studying products you admire, learning from competitors, or building analytical design thinking.

The English summary is being prepared. Showing the original description.

Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio. Expert in quantization formats (GGUF, EXL2) and local AI privacy.

The English summary is being prepared. Showing the original description.

Integrate and optimize Core ML models in iOS apps for on-device machine learning inference. Covers model loading (.mlmodelc, .mlpackage), predictions with auto-generated classes and MLFeatureProvider, compute unit configuration (CPU, GPU, Neural Engine), MLTensor, VNCoreMLRequest, MLComputePlan, multi-model pipelines, and deployment strategies. Use when loading Core ML models, making predictions, configuring compute units, or profiling model performance.

The English summary is being prepared. Showing the original description.

Choose OpenRouter models and routers, query live catalog data, use structured outputs and batch inference, and debug routing with metadata. Use when working with OpenRouter APIs, openrouter/auto, openrouter/free, model discovery, pricing, providers, batch jobs, or structured JSON responses.

The English summary is being prepared. Showing the original description.

Read release notes/changelogs, update a defined dependency scope, handle breaking changes, and verify. Explicit-only; no broad update-everything by inference.

The English summary is being prepared. Showing the original description.

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.

The English summary is being prepared. Showing the original description.

Speed up long-sequence transformer training and inference.

The English summary is being prepared. Showing the original description.

Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapt

The English summary is being prepared. Showing the original description.

Google Gemini API (Gemini Developer API, ai.google.dev) の Interactions API (v1 / v1beta), generateContent, Google GenAI SDK (google-genai / @google/genai), Live API, ephemeral tokens, Managed Agents, Deep Research, function calling, Google Search grounding, File Search, Files API, thought signatures, Nano Banana, Veo, Lyria, Batch API, Flex / Priority inference, OpenAI 互換。

The English summary is being prepared. Showing the original description.

Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.

The English summary is being prepared. Showing the original description.

Mendelian randomization (MR) causal inference — does an exposure, risk factor, or biomarker CAUSALLY affect a disease/outcome, using genetic variants as instrumental variables (IEU OpenGWAS / EpiGraphDB MR-EvE). Use this whenever the user asks if X causes Y, whether an observational association is actually causal or just correlation, if a biomarker/trait is a causal risk factor, wants to triangulate epidemiology against genetic evidence, or mentions Mendelian randomization, instrumental-variable analysis, two-sample MR, or genetic causal evidence — even if they never say "MR" (e.g. "is LDL cholesterol actually causal for heart disease?", "does BMI cause type 2 diabetes or just correlate?", "is CRP a causal driver of stroke?"). Covers trait-label resolution, MR effect direction/magnitude, instrument quality (MOE score), method agreement (IVW vs MR-Egger vs weighted median), bidirectional MR for reverse causation, and distinguishing causation from genetic correlation. Not for plain GWAS association lookups (use the GWAS skills) or fitting your own instruments from raw summary statistics.

The English summary is being prepared. Showing the original description.

Estimates the minimum biological replicates (or cells/events) for a target power at a target FDR in genomics experiments using ssizeRNA, PROPER, powsimR for scRNA-seq, and pilot-data dispersion estimation from DESeq2/edgeR. Covers the biological-versus-technical replication distinction (technical replicates do not add degrees of freedom for biological inference), replicate-number-versus-sequencing-depth budgeting, scRNA-seq sample-versus-cell allocation under a pseudobulk model, and the critique that "n=3" is a publication convention rather than a power calculation. Use when budgeting a sequencing experiment, writing the sample-size justification in a grant, estimating replicates from pilot data, allocating a fixed budget between samples and depth, or planning scRNA-seq cohort size. For clinical-trial sample size see clinical-biostatistics/power-and-sample-size; for the power-given-n direction see experimental-design/power-analysis.

The English summary is being prepared. Showing the original description.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

The English summary is being prepared. Showing the original description.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

The English summary is being prepared. Showing the original description.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

The English summary is being prepared. Showing the original description.

End-to-end outbreak investigation from pathogen isolates to transmission networks. Orchestrates MLST typing, AMR surveillance, phylodynamic dating, and transmission inference with TransPhylo. Use when investigating disease outbreaks or tracking pathogen transmission chains.

The English summary is being prepared. Showing the original description.

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

The English summary is being prepared. Showing the original description.

Builds and validates predictive time-to-event models on clinical and omics data with penalized Cox, random survival forests, gradient-boosted and deep survival models, and prediction-grade evaluation (Uno's C, time-dependent AUC, integrated Brier, calibration, competing risks). Use when building an individualized risk predictor or prognostic omics signature, choosing a survival model, or evaluating one beyond the C-index. For Kaplan-Meier, log-rank, and classical Cox hazard-ratio inference in a trial see clinical-biostatistics/survival-analysis.

The English summary is being prepared. Showing the original description.

Validates predictive models on omics and biomedical data with nested cross-validation, group/batch/temporal-aware splits, the full data-leakage taxonomy, probability calibration, decision-curve net benefit, optimism correction, sample-size planning, and TRIPOD+AI reporting. Use when estimating model performance honestly, choosing a CV scheme, detecting leakage, or judging whether reported discrimination means the model is actually useful. For feature selection itself see machine-learning/biomarker-discovery; for confirmatory-trial inference see clinical-biostatistics/trial-reporting.

The English summary is being prepared. Showing the original description.