Join us

FAUN.dev() is where engineers from GitHub, Netflix, and Shopify go to stay ahead — fast.

An effortless, straightforward way to keep up with technologies...so you can keep your tabs closed and your mind open!

70,000+ developers already joined our ecosystem ⭐⭐⭐⭐⭐
Trusted by engineers at:

Google • Microsoft • AWS • Netflix

vLLM

vLLM is a high-performance open-source inference and serving engine for large language models (LLMs), designed to maximize throughput and efficiency through optimized memory management and scheduling.

Featured Course(s)

Helm V4 in Practice

Designing, Deploying, and Operating Kubernetes Applications at Scale

> Get Your Copy

Content

Updates and recent posts about vLLM..

Posts
Description

Link

@anjali shared a link, 6 months, 3 weeks ago

Customer Marketing Manager, Last9

What Are AI Guardrails

Learn the core concepts of AI guardrails and how they create safer, more reliable, and well-structured AI systems in production.

grafana_tempo

Story

@laura_garcia shared a post, 6 months, 3 weeks ago

Software Developer, RELIANOID

🚨 AWS Outage Analysis: Lessons in Cloud Resilience

On October 20, 2025, AWS suffered a major disruption in its US-EAST-1 region, impacting over 140 services including EC2, Lambda, S3, and DynamoDB. The root cause? A DNS resolution failure that cascaded through dependent systems — showing how even the strongest cloud infrastructures can falter. At RE..

aws outage

Story

@laura_garcia shared a post, 6 months, 3 weeks ago

Software Developer, RELIANOID

🚀 Deploy RELIANOID Load Balancer Enterprise Edition v8 with Terraform on AWS

Our latest quick guide shows you how to spin up the RELIANOID Enterprise Edition on AWS in just a few commands — using the official Terraform module from the Terraform Registry. You’ll automatically provision: ✅ VPC + Internet Gateway ✅ Public Subnet ✅ Security Group (SSH 22, Web GUI 444) ✅ EC2 Inst..

terraform_relianoid_enterprise_img2

Link

@anjali shared a link, 6 months, 3 weeks ago

Customer Marketing Manager, Last9

Grafana Tempo: Setup, Configuration, and Best Practices

A practical guide to setting up Grafana Tempo, configuring key components, and understanding how to use tracing across your services.

grafana_tempo

Story

@laura_garcia shared a post, 6 months, 3 weeks ago

Software Developer, RELIANOID

🍺 Cyberattack on Asahi Group: A Wake-Up Call for Japan’s Industrial Sector

Just after Japan’s new Active Cyberdefence Law (ACD Law) came into effect — a major step toward reshaping the country’s cybersecurity posture — Japan’s largest brewer, Asahi Group, has suffered a ransomware attack that disrupted production and logistics nationwide. ⚠️ This incident starkly illustrat..

japan_brewery_ransomware_relianoid

Link

@varbear shared a link, 6 months, 3 weeks ago

FAUN.dev()

Free software scares normal people

A developer rolled outMagicbrake- a no-fuss GUI forHandbrakeaimed at folks who don’t speak command line. One button. Drag, drop, convert. Done. It strips Handbrake down to the bones for anyone who just wants their video in a different format without decoding flags and presets... read more

Link

@varbear shared a link, 6 months, 3 weeks ago

FAUN.dev()

How Netflix Tudum Supports 20 Million Users With CQRS

Netflix gutted Tudum’s old read path—Kafka, Cassandra, layers of cache—and swapped inRAW Hollow, a compressed, distributed, in-memory object store baked right into each microservice. Result? Homepage renders dropped from 1.4s to 0.4s. Editors get near-instant previews. No more read caches. No extern.. read more

How Netflix Tudum Supports 20 Million Users With CQRS

Link

@varbear shared a link, 6 months, 3 weeks ago

FAUN.dev()

uv is the best thing to happen to the Python ecosystem in a decade

uvis a new Rust-powered CLI from Astral that tosses Python versioning, virtualenvs, and dependency syncing into one blisteringly fast tool. It handles yourpyproject.tomllike a grown-up—auto-generates it, updates it, keeps your environments identical across machines. Need to run a tool once without t.. read more

uv is the best thing to happen to the Python ecosystem in a decade

Link

@varbear shared a link, 6 months, 3 weeks ago

FAUN.dev()

The bug that taught me more about PyTorch than years of using it

A sneaky bug inPyTorch’s MPS backendlet non-contiguous tensors silently ignore in-place ops likeaddcmul_. That’s optimizer-breaking stuff. The culprit? ThePlaceholder abstraction- meant to handle temp buffers under the hood - forgot to actually write results back to the original tensor... read more

The bug that taught me more about PyTorch than years of using it

Link

@varbear shared a link, 6 months, 3 weeks ago

FAUN.dev()

Kafka is fast -- I'll use Postgres

Postgres is pulling Kafka moves—without the Kafka. On a humble 3-node cluster, it held 5MB/s ingest and 25MB/s egress like a champ. Low latency. Rock-solid durability. Crank things up, andsingle-node Postgresflexed hard: 240 MiB/s in, 1.16 GiB/s out for pub/sub. Thousands of messages per second in q.. read more

Kafka is fast -- I'll use Postgres

vLLM is an advanced open-source framework for serving and running large language models efficiently at scale. Developed by researchers and engineers from UC Berkeley and adopted widely across the AI industry, vLLM focuses on optimizing inference performance through its innovative PagedAttention mechanism — a memory management system that enables near-zero waste in GPU memory utilization. It supports model parallelism, continuous batching, tensor parallelism, and dynamic batching across GPUs, making it ideal for real-world deployment of foundation models. vLLM integrates seamlessly with Hugging Face Transformers, OpenAI-compatible APIs, and popular orchestration tools like Ray Serve and Kubernetes. Its design allows developers and enterprises to host LLMs with reduced latency, lower hardware costs, and increased throughput, powering everything from chatbots to enterprise-scale AI services.