Baseten, NVIDIA Dynamo and SGLang to host SF meetup on RL post-training infrastructure
BanghuaZ · x · 2026-09-03
SGLang announced a joint evening meetup with Baseten and NVIDIA Dynamo in San Francisco on September 10, focused on the infrastructure behind RL post-training.
- The event will feature the latest on SGLang and Miles, an RL training framework that uses SGLang as its rollout inference engine to make RL post-training fast and reliable
- Agenda includes three technical talks from Baseten, Dynamo, and SGLang (6:30-7:15 pm), followed by developer networking
- Topics span high-throughput inference, efficient rollouts, and fault-tolerant infrastructure, with 151 attendees registered
Related event: Baseten, NVIDIA Dynamo and SGLang to Host RL Post-Training Infra Meetup(2 posts)→
More from Companies & People
- Twilio dev advocate Craig Dennis joins OpenAI, recounts pre-ChatGPT LLM demos generating TwiML — craigsdennis · 2026-09-03
- Berkeley Tops PitchBook for Undergrad Founders 4th Straight Year: 2,155 VC-Backed Startups — jfiance · 2026-09-03
- Uber lays off 3,300 people, 10% of staff, to flatten management and boost robotaxi bets — saibharadwaj · 2026-09-03
- Anders Sandberg to speak on human autonomy in the AI age at EAGx Oxford, Sept 25-27 — anderssandberg · 2026-09-03
- Devnexus, largest US Java conference, retools 2027 around AI with 10 tracks — mkheck · 2026-09-03
- Auth0Lab opens up: first public look at how it does 0-to-1 products — yenkel · 2026-09-03