Frye's session will analyze vLLM, SGLang, and TRT-LLM systems
Giving a workshop at @aiDotEngineer World's Fair, going over the architecture and implementation of inference engines like @sgl_project and @vllm_project.
https://www.ai.engineer/worldsfair/schedule?session=asn_slot_2026_06_29_workshop_track_09_1105_2026_06_13t06_25_55_037z
Many users expressed excitement for Charles Frye's workshop on inference engine architecture, citing the need for dedicated inference conferences and looking forward to watching the video.
No Digg Deeper questions have been answered for this story yet.
@charles_irl @aiDotEngineer @sgl_project @vllm_project surely we’d call it inference engineering summit?? @philipkiely
@aiDotEngineer @sgl_project @vllm_project @swyx AI Backend Engineer Summit wen
@charles_irl @sgl_project @vllm_project very very needed! we need to split out an entire inference conf at somepoint because as large as WF is I actually feel strongly we are UNDER covering this relative to their importance
@aiDotEngineer @sgl_project @vllm_project @swyx AI Backend Engineer Summit wen
@swyx @aiDotEngineer @sgl_project @vllm_project @philipkiely d
@charles_irl @aiDotEngineer @sgl_project @vllm_project surely we’d call it inference engineering summit?? @philipkiely
@charles_irl @aiDotEngineer @sgl_project @vllm_project Can’t wait to watch the vod later
@charles_irl @aiDotEngineer @sgl_project @vllm_project what's the latency floor for realtime robotics inference? batch size of 1 on current hardware?
