LLAMA A Low Latency Math Library for Secure Inference

Name: LLAMA A Low Latency Math Library for Secure Inference
Uploaded: 2022-01-01
Duration: 12 min 21 s
Description: LLAMA A Low Latency Math Library for Secure Inference — a 2022 PETS 2022 security conference talk on ai-ml (12:21 min). Watch the full video, indexed free on the Breach Arc Archive.

PETS 2022 · 2022 · 12:21

▶

LLAMA A Low Latency Math Library for Secure Inference — a 2022 PETS 2022 security conference talk on ai-ml (12:21 min). Watch the full video, indexed free on the Breach Arc Archive.

▶ Watch video on YouTube

ai-ml

← Back to the Breach Arc Archive