Tag: #load-balancing
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 9 posts
MoE Routing — How an Expert Gets Picked
Reading the config fields of a mixture-of-experts layer against real models. Comparing Mixtral 2-of-8, Qwen3 8-of-128, the 256 routed experts plus a shared expert in DeepSeek-V3, and the sparsity of 48 in Kimi K2, then w
2026-08-12 · 6 min read #ai-papers#model-internals#mixture-of-experts#moe#routingHAProxy Ingress Controller — A Battle-Tested Load Balancer Enters Kubernetes
A deep dive into how HAProxy, a load balancer proven over more than two decades, enters Kubernetes as an ingress controller. We cover the difference between the official haproxytech project and the community jcmoraisjr p
2026-06-14 · 20 min read #haproxy#ingress#kubernetes#load-balancing#networkingConsistent Hashing Complete Guide 2025: Virtual Nodes, Jump Hash, Rendezvous, and the Core Building Block of Distributed Systems
How DynamoDB, Cassandra, and Memcached minimize data movement when nodes are added or removed. A 700-line deep dive on Consistent Hashing, from first principles to virtual nodes (vnodes), Jump Hash, Rendezvous Hashing, a
2026-04-15 · 16 min read #consistent-hashing#distributed-systems#sharding#virtual-nodes#jump-hashAPI Gateway Complete Guide 2025: Kong, Envoy, AWS API Gateway, Auth/Rate Limiting/Monitoring
Everything about API Gateways! Kong vs Envoy vs AWS API Gateway vs Traefik comparison, routing, authentication (OAuth2/JWT/API Key), rate limiting (Token Bucket/Sliding Window), request transformation, caching, monitorin
2026-04-14 · 24 min read #api-gateway#kong#envoy#aws-api-gateway#rate-limitingSystem Design Interview Complete Guide 2025: Scalable Architecture, Availability, and Design Patterns
Everything about system design interviews! 4-step framework, scalability (horizontal/vertical), load balancing, caching (Redis/CDN), DB sharding, CAP theorem, message queues, real-world designs (URL Shortener/Twitter/Net
2026-03-25 · 21 min read #system-design#scalability#availability#load-balancing#cachingLiteLLM Complete Guide 2025: Unify 100+ LLMs with a Single API Proxy Server
Everything about LiteLLM! 100+ LLM unified API, OpenAI-compatible proxy server, cost tracking/budget management, load balancing/fallback, model routing, virtual keys, rate limiting, Guardrails, production deployment (Doc
2026-03-25 · 18 min read #litellm#llm#api#proxy#openaiNginx Complete Guide 2025: Reverse Proxy, Load Balancing, SSL, Caching & Security
Everything about Nginx! Event-driven architecture, reverse proxy configuration, load balancing (Round Robin/Least Conn/IP Hash), SSL/TLS setup, caching, rate limiting, WebSocket, Docker/K8s integration, and more.
2026-03-24 · 18 min read #nginx#reverse-proxy#load-balancing#ssl#cachingThe Complete Guide to Redundancy — The Secret Behind 99.999% Availability
From dual redundancy to triple redundancy, Active-Standby, Active-Active, N+1, split brain, and quorum. We explain why the difference between 99.9% and 99.999% translates to 8 hours vs. 5 minutes of annual downtime, with
2026-03-02 · 8 min read #architecture#high-availability#redundancy#failover#load-balancingNginx Configuration Complete Guide: 15 Essential Topics from Architecture to Production Optimization
From Nginx event-driven architecture and configuration structure to reverse proxy, load balancing, SSL/TLS, caching, rate limiting, security headers, performance tuning, and health checks -- a comprehensive guide to 15 e
2026-03-01 · 33 min read #nginx#reverse-proxy#load-balancing#ssl#tls