LoRAX: Serve 1000s of Fine-Tuned LLMs on a Single GPU
Provides loRAX: Serve 1000s of Fine-Tuned LLMs on a Single GPU and evaluates key implications for security practitioners.
Summary
No summary yet — watch the video above, or open it on YouTube.
Related talks
The Linux Foundation·30 min
Sean Isom · Mendy Berger
Demonstrates wasi-Webgpu: Build Beautiful Graphics and Safely Run AI with Any GPU and evaluates key implications for security practitioners.
gpuwasi-webgpubuild+2
Eye on Tech·44 min
Engineers explore architecture and security mechanisms for AI speech-to-text eavesdropping can serve the greater good.
eavesdroppingspeech-to-textserve+2
FIRST·28 min
Presenters detail vulnerability discovery and exploitation in Dark Silicon: Unmasking GPU Threats in the Age of AI.
aigpusilicon