Compression at the Edge
Chris Alexiuk, Daniel Han, Asma Beevi, Merve Noyan, Parth Sareen
- When
- Thursday, July 22:25 PM – 2:45 PM · 20 min
- Where
- Track 4San Francisco, CA · imported from ai.engineer's public schedule feed
About this session
Compression at the Edge examines how smaller weights, faster inference, and constrained-memory deployments are making capable local AI more practical. The panel explores where compressed models already beat cloud on latency, privacy, cost, or control, what breakthroughs would unlock broader adoption, and how open model tooling is shaping the edge AI stack.
Moderator: Chris Alexiuk (NVIDIA). Panelists: Daniel Han (Unsloth), Asma Beevi (NVIDIA), Merve Noyan (Hugging Face), Michael Chiang (Ollama).
Speakers (5)
Sr. Product Research Engineer, NVIDIA
Chris Alexiuk is a Sr. Product Research Engineer at NVIDIA, he is obsessed with everything and anything about large language models as well as Dungeons & Dragons.
Co-founder, Unsloth
Co-founder of Unsloth. Making open source AI more accessible and local. 300M downloads. 65K GitHub stars. Previously at NVIDIA.
Senior Engineer, NVIDIA
Asma Beevi K T is a senior engineer at NVIDIA, developing the NVIDIA TensorRT Model Optimizer toolkit. Her interests span training and inference optimizations for deep learning models, particularly LLMs.
MLE, Hugging Face
Works at Hugging Face open-source team, author of the book Vision Language Models with Hugging Face published by O'Reilly.
Ollama
More in Local AI
- State of the Union: Why Local, Why NowThursday, July 2 · 10:45 AM – 11:05 AM · Track 4
- State of the Union: Why Local, Why NowThursday, July 2 · 11:10 AM – 11:30 AM · Track 4
- Demo: GLM 5.2 on DGX Station — Frontier Intelligence Under Your DeskThursday, July 2 · 11:40 AM – 12:00 PM · Track 4
- Local AI DemosThursday, July 2 · 12:05 PM – 12:25 PM · Track 4
- Local Models: Trust, Control, OptimizationThursday, July 2 · 1:30 PM – 1:50 PM · Track 4
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.