Official event by the vLLM creators
vLLMBangkok Day
A day of production vLLM — talks from the creators, real Thai deployments, and the people building inference infrastructure in Southeast Asia.
- When
- Sunday, 6 September 2026 · 14:00–19:00
- Where
- JAS Green Village Ramkhamhaeng
Registration is full

Counting down to vLLM Bangkok Day
The event starts on Sunday, 6 September 2026, 14:00–19:00 (ICT).
We're live right now
Sessions are running at the venue.
That was vLLM Bangkok Day
Thanks to everyone who came. Recaps and talks are on the blog.
Read the recapOn the day
The visuals running on the main LED wall and the entrance screens at JAS Green Village.
Autoplay is off because your device prefers reduced motion.
What is vLLM Bangkok Day?
vLLM is the open-source inference engine behind a large share of the world’s LLM serving. For one afternoon its creators come to Bangkok to show how it is built and how it is run at scale — and to meet the Thai teams already running it in production.
- When
- Sunday, 6 September 2026
- Doors open 13:15 · 14:00–19:00 · Bangkok time (ICT, UTC+7)
- Where
- JAS Green Village Ramkhamhaeng
- 3rd floor · Rat Phatthana, Saphan Sung, Bangkok
- Cost
- Free — registration closed
- 250 Thai & international attendees
What to expect
Talks by the vLLM creators
Core maintainers from the USA and Singapore on the internals — paged attention, continuous batching, and where the project is heading.
Real production use cases
Thai companies, developers and researchers on what actually broke, what it cost, and what they would do differently.
Enterprise & technical sessions
Deployment patterns, GPU economics, and serving Thai-language models at production latency.
Networking between Thailand and the world
Structured time to meet the international vLLM community and the people building AI infrastructure here.
Registration is full
The programme
Ten sessions, two panels, one afternoon. Times are Bangkok time.
- – 14:00Live nowRegistration
Registration & doors open
- – 14:20Live nowOpening
Opening — introducing the vLLM roadmap in the Thailand ecosystem
AGICAFET (AGICAFET)
- – 14:50Live nowTalk
Introduction to vLLM: High-Performance LLM Serving & Maximizing Performance on Limited GPUs
Tun Jian Tan (Embedded LLM)
- – 15:45Live nowPanel
Panel — AI Adoption in Thailand: what actually works
Dr Pin Siang Tan (Embedded LLM) · Tuan Luong (Tensormesh) · Dr Komes Chandavimol (KBTG) · Moderator: Yim
- – 16:00Live nowTalk
Thai and global perspective: the connected point
CK (Fastwork)
- – 16:30Live nowTalk
Inside vLLM: Production Best Practices, Model Integration and Road Map
Tiezhen WANG (Inferact)
- – 17:00Live nowTalk
Scaling Distributed Inference with llm-d
Jing Wen Ng (Red Hat)
- – 17:30Live nowTalk
Supercharging vLLM with LMCache: KV-Cache Reuse in Practice
Dai Tran (Tensormesh)
- – 17:45Live nowBreak
Break
- – 18:20Live nowPanel
Panel — vLLM Developers in Thailand
Sattaya Singkul (True Digital Group) · Natthanan Bhukan (Tsinghua University) · Pongsasit Thongpramoon (NVIDIA)
- – 19:00Live nowNetworking
Lucky draw & networking
vLLM in Thailand
The companies, labs and universities running vLLM here. If your team is on this list, you are not doing it alone.

