Skill UI

Activation-aware weight quantization that compresses 7B-70B models to 4-bit with minimal accuracy loss, delivering ~3x inference speedups and memory reductions for constrained GPU deployments while integrating with vLLM and Marlin kernels.

Guides ML teams through automated batch inference pipelines, suggesting best practices, monitoring and production readiness, and generating code and configs for deployment.

A comprehensive guide to understanding the complete state (context) available to Large Language Models during inference. Covers core components like System Prompts, Tool Definitions, Message History, and Retrieval Augmented Generation (RAG). Learning to engineer context is crucial for building robust, efficient, and reliable AI agent systems by managing the attention budget and ensuring high-signal information delivery.

This guide outlines the complete MLOps workflow on Databricks. It covers feature engineering using Feature Store, tracking experiments with MLflow, managing model versions in the Model Registry, and deploying real-time inference endpoints via Mosaic AI Model Serving. Ideal for building robust, production-grade ML pipelines.

This guide details the use of the GGUF format and quantization techniques for running large language models (LLMs) efficiently. GGUF enables optimal inference on consumer hardware, Apple Silicon, and systems requiring CPU-only operation. By compressing models using various K-quant methods (like Q4_K_M), developers can significantly reduce memory footprint and hardware requirements while maintaining high performance.

GPTQ enables post-training 4-bit quantization for large LLMs, delivering up to 4× memory reduction and 3-4× faster inference with under 2% perplexity loss on consumer GPUs through AutoGPTQ, PEFT, and Transformer integrations.

This guide details a production-ready reference architecture for applications built on Groq's LPU inference API. It covers sophisticated model routing based on latency, quality, or cost needs, implementing streaming pipelines, and establishing robust multi-provider fallback chains (e.g., Groq primary to OpenAI backup). Ideal for designing and reviewing complex, resilient LLM systems.

GroqCloud Automation orchestrates high-performance GroqCloud APIs through Composio, covering inference, chat completions, audio translation, and TTS voice selection for production workflows.

Execute complex and compute-intensive workloads directly on fully managed Hugging Face cloud infrastructure. This skill eliminates the need for local setup, allowing users to run jobs using cloud CPUs, GPUs, or TPUs. Ideal for large-scale data processing, batch inference, reproducible model training, and scheduled automation tasks, while persisting results to the Hugging Face Hub.

Automates inference latency profiler tasks in ML deployment scenarios, offering step-by-step guidance on model serving, MLOps pipelines, monitoring, and production optimization, generating production-ready code and validating outputs against best practices.

Knowledge Distillation is a crucial technique used to compress large, high-performing Language Models (Teacher) into smaller, more efficient Student models. This allows developers to deploy powerful AI capabilities (like those of GPT-4) on resource-constrained devices while significantly reducing inference costs. The method uses advanced techniques such as soft targets, temperature scaling, and Reverse KL Divergence (MiniLLM) to transfer knowledge effectively.

Playbook for running ML training and inference on Lambda Labs’ on-demand GPU cloud, covering when to choose it, console/SSH/API workflows, available GPUs, pricing, and persistent storage with Lambda Stack pre-installed.