≈ the.bay.news

Decode Speed Is Bytes Divided by Bandwidth, and the Batch Ceiling Is 848 Tokens

DEV Community
Decode Speed Is Bytes Divided by Bandwidth, and the Batch Ceiling Is 848 Tokens
At batch 1 decode is a traffic budget. Here is the formula for three models on an H100, the context past which batching stops helping, and why quantizing everything moves the wall without moving the distance to it.

0 comments

Sign in to join the discussion — your thebay.events account works here.

No comments yet.