From a2acaab7ceebd76f9e83e772e9d372f681ba9a37 Mon Sep 17 00:00:00 2001 From: DouJS Date: Wed, 18 May 2022 15:33:40 +0800 Subject: [PATCH] Update README.md polish readme --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 0fdd693..69a78ec 100644 --- a/README.md +++ b/README.md @@ -59,16 +59,16 @@ Here GPT3-12-layers in FP16 is adopted. Here a node with 8 A100 80 GB GPUs is adopted. GPUs are fully connected with NvLink. Energon adopts the redundant computation elimination method from [EffectiveTransformer](https://github.com/bytedance/effective_transformer) and the sequence length is set the half of the padding length.
- Architecture + Architecture
#### Latency Here GPT3 in FP16 is adopted. Here a node with 8 A100 80 GB GPUs is adopted. Every two GPUs are connected with NvLink. Here the sequence length is set the half of the padding length. -FasterTransformer does not support the redundant computation elimination method in distributed execution. +Here FasterTransformer is adopted in comparison and it does not support the redundant computation elimination method in distributed execution.
- Architecture + Architecture
### Contributing