Open and welcoming
Whether you are deploying your first model or operating at scale, you are welcome to learn and participate.
Our purpose
InferenceOps brings together engineers, researchers, platform teams, and builders to understand what it takes to run AI in production. Our purpose is to make practical inference knowledge easier to find, apply, and improve—from choosing models and serving runtimes to managing GPUs, routing requests, observing performance, and balancing latency, throughput, quality, and cost.
We learn through the experience of people building and operating real systems. By sharing deployment patterns, benchmarks, troubleshooting approaches, and lessons from both successes and failures, we help practitioners make informed decisions and adapt proven ideas to their own workloads and constraints.
Through field notes, reusable blueprints, workshops, and open discussion, we create space for people to ask questions, test ideas, and contribute at every stage of their journey. Together, we aim to turn individual experience into shared engineering knowledge and strengthen the practices that make AI inference reliable, efficient, and accessible.
Our principles
Practical and evidence-based
Share the conditions behind results, explain tradeoffs, and make room for correction.
Vendor-neutral and community-led
Build shared knowledge across technologies, organizations, and experience levels.
Core Members
People helping shape the direction of the community.
Core Member
Ritesh Shah
Ritesh Shah is a Senior Principal Architect with the Red Hat Portfolio Product Marketing and Learning team and…
Core Member
Prasad Mukhedkar
Prasad Mukhedkar is an AI Architect at Red Hat, specializing in AI inference, OpenShift AI, vLLM, LLMd and…
Core Member
Humble Devassy C
Humble Devassy Chirammal is a seasoned software engineer, author, and open-source advocate with over two decades of experience…
Core Member
Ompragash Viswanathan
Ompragash has a knack for Automation and AI and currently serves as a Product Manager at Harness. When…
Featured Members
Practitioners sharing useful technical knowledge and experience with the community.
Featured Member
Akhil Gupta
I’m a Product and Technology Leader with 15+ years of experience building AI-driven, enterprise-scale platforms across banking, SaaS,…
Community Contributors and Community Stewards
Community Contributors
People who share useful technical knowledge through articles, reviews, blueprints, corrections, or sessions.
Community Stewards
Practitioners who consistently review content, organize sessions, mentor contributors, improve resources, and support operations.
Recognition through service
Quality, usefulness, technical contribution, consistency, and community impact guide recognition. There are no activity quotas or promised credentials.
The InferenceOps Standard
Practitioner-led
Knowledge comes from people building, operating, researching, or closely studying real inference systems.
Evidence over hype
Performance, cost, and comparison claims include assumptions, methodology, sources, and limitations.
Vendor-neutral
Discuss tools deeply to teach an engineering lesson. Disclose affiliations; avoid product promotion.
Transparent
Authors disclose affiliations and relevant conflicts of interest.
Open to correction
Readers can question, correct, and improve published material as technical knowledge evolves.
Community-first
Help practitioners make better engineering decisions, with room for beginners and experienced contributors alike.
What open means here
Community knowledge is available to read without an account. Participation is open and publishing is editorially reviewed. Public access does not grant a blanket reuse license; follow any license stated on individual contributions or seek the rights holder’s permission.