vLLM Inference Meetup Mumbai
Join us for our first ever vLLM and llm-d AI inferencing meetup in Mumbai, where we will focus on the architecture, optimizations, and raw engineering required to run inference at scale.
Whether you’re looking to squeeze every last token out of your GPU cluster or you're curious about the latest commits to the vLLM and llm-d ecosystems, this is the room you want to be in.
Important: IIT Bombay Gate Pass Requirements
All attendees will receive a separate form to submit their full name, email ID, contact number, gender, and a copy of their Aadhaar or PAN card.
Submitting this information is mandatory to arrange entry passes for IIT Bombay
What to Expect
Deep Technical Sessions: Hear directly from the maintainers and core committers of vLLM and llm-d
Scale in Production: Learn from industry leaders about deploying LLMs in production
Networking: Stick around for food and soft drinks. It’s a great chance to chat with the speakers and exchange ideas with fellow developers and engineers.
Who Should Attend
vLLM and llm-d users and contributors
ML and infra engineers working on inference and serving
Platform teams running GenAI in production
Anyone curious about efficient inference across local, cloud, and Kubernetes
Event Agenda
1:00 – 1:30 PM | Registration & Networking
Check-in, meet fellow AI practitioners, and connect with the community.
1:30 – 1:45 PM | Opening Keynote: Why AI Inference Matters
Kick off the meetup with a look at the growing importance of scalable, efficient AI inference.
1:45 – 2:00 PM | What's New in vLLM and llm-d
Speakers: Prasad Mukhedkar & Ompragash Viswanathan
Explore the latest developments, capabilities, and innovations across vLLM and llm-d.
2:00 – 2:30 PM | Inside vLLM Semantic Router: Intelligent Routing for LLM Inference
Speakers: Ritesh Shah & Suresh Gaikwad, Red Hat
Discover how intelligent, semantic-aware routing optimizes model selection, inference performance, and resource utilization.
2:30 – 3:00 PM | Scaling AI Inference at NxtGen with the vLLM Ecosystem
Speaker: Abhishek Kumar Singh, NxtGen
Learn how NxtGen leverages the vLLM ecosystem to scale production AI inference workloads.
3:00 – 3:30 PM | Networking, Tea & Snacks
Take a break, exchange ideas, and connect with speakers and fellow attendees.
3:30 – 4:00 PM | Distributed Inference on AMD ROCm with WideEP, vLLM & llm-d
Speaker: Ajith Sirra, AMD
Explore distributed inference on AMD accelerators using ROCm, WideEP, vLLM, and llm-d.
4:00 – 4:30 PM | Crash-Safe vLLM Inference at Scale
Speaker: Anirudh Srinivasan, BharatGen
Learn how to build fault-tolerant, large-scale offline inference pipelines using vLLM, ensuring reliable processing and recovery from failures.
4:30 – 5:30 PM | Hands-on Workshop: Running vLLM on AMD Accelerators
Aditya Sivagnanam, AMD
Get hands-on experience deploying and running vLLM on AMD accelerators.
5:30 – 6:00 PM | Closing Remarks & Community Networking
Wrap up the meetup and continue conversations with the community.