'inference' 검색 결과

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing GPU memory use with long sequences
• Integrating Flash Attention into PyTorch models
• Comparing runtime and outputs before and after changes

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preprocessing datasets larger than memory
• Running batch predictions across multiple GPUs
• Preparing image and tabular data for training

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run language models with limited GPU memory
• Convert your own model to 4-bit weights
• Compare compression settings for quality and speed

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compressing a model without calibration data
• Comparing 4-bit and 2-bit quantization settings
• Running quantized models with HuggingFace Transformers or vLLM

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running GPU inference without managing servers
• Deploying a model as an automatically scaling API
• Processing large batches in parallel

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether a model fits on a GPU
• Compare memory estimates for GGUF quantizations
• Estimate KV cache memory for a chosen context length

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing workflows that run AI coding agents
• Tracing issue and PR content into agent prompts
• Checking sandbox settings and user allowlists

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Defining a process for recurring competitive research
• Separating sourced facts from AI interpretations
• Comparing findings across quarterly investigations

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Cross-check signs of a competitor's planned market entry
• Find evidence for market size estimates
• Choose sources for a competitive research plan

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing batching and request scheduling options
• Checking memory capacity for concurrent requests
• Assessing cache reuse and offloading tradeoffs

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Integrating chat and image generation into an application
• Preparing model fine-tuning jobs
• Checking balances and funding provider accounts

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running long GPU inference jobs on a remote host
• Submitting scientific workloads through Slurm
• Collecting and analyzing completed job outputs

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Interpret regression coefficients and confidence intervals
• Model binary outcomes or event counts
• Forecast time series with uncertainty intervals

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing priors for models with small datasets
• Implementing hierarchical models in Stan or PyMC
• Investigating MCMC convergence problems

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a causal method for evaluating a policy change
• Analyzing policies introduced at different times across regions
• Checking instrumental variable strength and underlying assumptions

Build a Python workflow for empirical research, from data cleaning and statistical checks to estimation, robustness checks, and paper-ready tables and figures. Economics is the default, with additional modes for epidemiology, public health, and machine learning for causal inference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building an end-to-end empirical analysis workflow in Python
• Replicating an applied economics paper
• Producing regression tables and event-study plots

Build and evaluate Bayesian models with PyMC and ArviZ, from choosing initial assumptions to checking predictions. The workflow covers sampling diagnostics, model comparison, and reports that explain results with uncertainty intervals.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose and check prior distributions
• Investigate sampling and convergence problems
• Compare hierarchical or regression models

Build Python code for economic models and policy evaluation, with guidance on choosing libraries, estimating effects, plotting results, and checking robustness. Covers macroeconomic simulation and causal inference, the analysis of cause and effect.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing macroeconomic models in Python
• Estimating policy effects with difference-in-differences
• Checking assumptions and robustness in causal analysis

Build a reproducible Stata analysis from data cleaning through modeling, diagnostic checks, and robustness tests. Generate runnable .do files, regression tables, and figures for empirical papers, with additional workflows for epidemiology and machine learning approaches to causal inference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a reproducible Stata analysis pipeline
• Comparing regression specifications in a paper table
• Checking causal estimates with robustness tests

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run TAO Data Services KPI analysis for object detection, comparing inference annotations against ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP at a fixed IoU. Use when an object detection workflow needs per-class mAP reported after inference, or when the user asks to "run KPI analyze", "compute detection mAP", or "score my OD predictions against ground truth".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evidence packs to MLflow. Use after inference, including NV-Generate runs; not for live training tracking, model registration, or clinical use.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.