From 5a427dbed17ccec0851a0a9fc5222c58db593e1e Mon Sep 17 00:00:00 2001 From: zR <2448370773@qq.com> Date: Thu, 19 Sep 2024 00:55:24 +0800 Subject: [PATCH] torchao --- README.md | 4 ++++ README_ja.md | 3 +++ README_zh.md | 3 +++ 3 files changed, 10 insertions(+) diff --git a/README.md b/README.md index 43ea2f8..0c66b77 100644 --- a/README.md +++ b/README.md @@ -114,6 +114,10 @@ pip install -r requirements.txt Then follow [diffusers_demo](inference/cli_demo.py): A more detailed explanation of the inference code, mentioning the significance of common parameters. +For more details on quantized inference, please refer +to [diffusers-torchao](https://github.com/sayakpaul/diffusers-torchao/). A full list of memory and time benchmarks with +various settings on A100 and H100 has been published there. + ## Gallery ### CogVideoX-5B diff --git a/README_ja.md b/README_ja.md index c8a8bf9..6d4fa3f 100644 --- a/README_ja.md +++ b/README_ja.md @@ -97,6 +97,9 @@ pip install -r requirements.txt 次に [diffusers_demo](inference/cli_demo.py) を参照してください: 推論コードの詳細な説明が含まれており、一般的なパラメータの意味についても言及しています。 +量子化推論に関する詳細は、[diffusers-torchao](https://github.com/sayakpaul/diffusers-torchao/) +をご覧ください。A100とH100における様々な設定でのメモリおよび時間のベンチマークリストが公開されています。 + ## Gallery ### CogVideoX-5B diff --git a/README_zh.md b/README_zh.md index 3ced98c..836ad41 100644 --- a/README_zh.md +++ b/README_zh.md @@ -93,6 +93,9 @@ pip install -r requirements.txt 查看[diffusers_demo](inference/cli_demo.py):包含对推理代码更详细的解释,包括各种关键的参数。 +关于量化推理的更多细节,请查看[diffusers-torchao](https://github.com/sayakpaul/diffusers-torchao/) +。这里发布了一份完整的内存和时间基准测试列表,涵盖了A100和H100上的各种设置。 + ## 视频作品 ### CogVideoX-5B