Skip to content
tezvyn:

Mlops

265 bites tagged Mlops — interview questions with model answers, and 60-second explainers.

MLOps & Infrastructure2 min read

BentoML: Packaging Models for Production APIs

BentoML is a standardized shipping container for your ML models, packaging them into production-ready API endpoints. Use it to deploy LLMs or RAG systems without managing complex infrastructure. Its focus is purely on inference, not model training.

MLOps & Infrastructure2 min read

Autoscaling ML Inference Endpoints

Autoscaling matches your ML model's compute to real-time demand, like an elastic container for your inference service. It handles spiky traffic for online endpoints, scaling up for peaks and down to save costs.

MLOps & Infrastructure2 min read

Inference Batching: Grouping Requests for Throughput

Think of inference batching as a carpool for your ML model. Instead of sending each request in its own car, you wait a few microseconds to fill a bus, dramatically improving GPU efficiency.

MLOps & Infrastructure2 min read

TorchServe: Serving PyTorch Models in Production

TorchServe is a web server for your PyTorch models, turning them into production-ready API endpoints. It's used to expose trained models over a network via REST or gRPC for inference, handling batching and multi-model serving.

MLOps & Infrastructure2 min read

LLM Inference Caching: Pay for Computation Once

LLM inference caching reuses past computations to cut costs and latency. It avoids reprocessing shared system prompts or serves full answers for common queries without hitting the model. The footgun: semantic caches can return a "similar" but incorrect answer.

MLOps & Infrastructure2 min read

Load Balancing for Model Serving

A load balancer is a traffic cop for your AI model's API, directing requests to multiple model copies to prevent overload. It's essential for production systems to ensure high availability. The footgun is forgetting health checks, causing failed requests.

MLOps & Infrastructure2 min read

NVIDIA Triton: A Universal AI Model Server

Triton Inference Server is like a universal remote for AI models, providing a standard API to serve models from any framework. Use it to deploy diverse models (PyTorch, ONNX) without custom serving stacks.

MLOps & Infrastructure2 min read

Multi-Armed Bandits for Model Selection

Treat your candidate models like slot machines. A Multi-Armed Bandit (MAB) algorithm automatically allocates traffic to find the best one, balancing exploration of new options with exploiting the current winner.

MLOps & Infrastructure2 min read

Edge AI: Running Models Where the Data Is

Edge AI runs machine learning models directly on devices, not in a distant cloud. This enables real-time, offline applications like smart cameras or voice assistants. The footgun is underestimating device hardware limits; models must be small and efficient.

MLOps & Infrastructure2 min read

Streaming Inference: Real-Time Model Predictions

Streaming inference makes predictions on data in-flight, not from a database. It's for real-time recommendations or fraud detection where millisecond decisions are critical. The footgun is assuming a single server can handle the load; you must build for scale.

MLOps & Infrastructure2 min read

Serverless Inference: Run ML Models Without Managing Servers

Serverless inference treats ML prediction like a function call, abstracting away servers. You pay for compute time per prediction, not for idle infrastructure.

MLOps & Infrastructure2 min read

Batch Inference: High Throughput, Not High Speed

Think of batch inference as processing a day's mail at once, not as each letter arrives. It trades immediate answers for cost-effective, high-volume predictions, like generating daily product recommendations. The footgun is using it for real-time needs.

MLOps & Infrastructure2 min read

Online Inference: Predictions on Demand

Online inference is a vending machine for predictions: you make one request and get one result back immediately. It powers real-time features like fraud detection or content moderation.

MLOps & Infrastructure1 min read

GitOps for MLOps: Your ML System as Code

GitOps for MLOps treats your entire machine learning pipeline—data, code, and models—as declarative configuration in Git. It automates ML workflows, ensuring reproducibility by making every change a reviewable commit.

MLOps & Infrastructure2 min read

Automating MLOps with GitHub Actions

Treat your ML workflow like any other CI/CD pipeline. GitHub Actions automates MLOps tasks—like training, testing, and deployment—triggered by events in your repo. Use it to run validation on PRs or deploy models on merge.

MLOps & Infrastructure2 min read

Unit Testing ML: Beyond Standard Code Checks

Unit testing for ML isn't just about code logic; it's about checking data, models, and infrastructure in isolation. Use it to validate data transformers, check model prediction shapes, or confirm a function handles nulls.

MLOps & Infrastructure2 min read

Microsoft DeepSpeed: Training Massive Models Across GPUs

DeepSpeed trains models too big for one GPU by partitioning model states across many devices. It's essential for training foundation models like BLOOM, but its complexity is overkill for smaller models and misconfiguration can harm performance.

MLOps & Infrastructure2 min read

All-Reduce: Synchronizing Parallel Workers

All-Reduce lets parallel workers agree on a global result. Each worker contributes data, an operation (like sum) runs on all data, and every worker gets the final answer. It's the core of distributed ML training, used to average gradients across GPUs.

MLOps & Infrastructure2 min read

Elastic Training: Training Models on Unreliable Hardware

Elastic Training lets ML training jobs survive worker nodes being added or removed mid-run. It's like a construction crew that adapts to a changing number of workers, making it ideal for training large models on cheap but unreliable cloud spot instances.

MLOps & Infrastructure2 min read

Slurm: The Job Scheduler for Supercomputers

Slurm is the reservation system for a shared supercomputer, queuing up jobs and assigning them to available nodes. It's the backbone of high-performance computing clusters in science and ML.

MLOps & Infrastructure2 min read

Kubeflow: MLOps on Kubernetes

Kubeflow brings the declarative, container-based world of Kubernetes to the entire ML lifecycle. It provides tools for building portable and scalable ML workflows, from development to production serving.

MLOps & Infrastructure2 min read

Ray AI Runtime (AIR): A Unified ML Toolkit

Ray AIR is a unified toolbox for the ML lifecycle, bundling libraries for data, training, tuning, and serving. It's for scaling end-to-end ML workflows on one distributed platform.

MLOps & Infrastructure2 min read

Horovod: Scale ML Training Across Many GPUs

Horovod scales a single-GPU training script to hundreds of GPUs with minimal code changes, slashing training time. It's used when models are too big for one machine.

MLOps & Infrastructure2 min read

Parameter Servers for Distributed ML Training

A parameter server splits the work in distributed training: central servers hold the model's parameters, while worker nodes pull parameters, compute gradients on data subsets, and push updates back. This enables training models too large for one machine.

Get Mlops bites daily.

Five a day, five minutes, offline. With quizzes so it sticks.

Open testing — you’ll join as an early tester.