From 1d15901d244a22a224d5cc3598ea39c91624f5cd Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Thu, 1 Feb 2024 15:51:15 +0000 Subject: [PATCH] Update docs2. --- docs/source/basic_tutorials/launcher.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/source/basic_tutorials/launcher.md b/docs/source/basic_tutorials/launcher.md index 712b4fc4..9c9d4d35 100644 --- a/docs/source/basic_tutorials/launcher.md +++ b/docs/source/basic_tutorials/launcher.md @@ -66,6 +66,7 @@ Options: - bitsandbytes: Bitsandbytes 8bit. Can be applied on any model, will cut the memory requirement in half, but it is known that the model will be much slower to run than the native f16 - bitsandbytes-nf4: Bitsandbytes 4bit. Can be applied on any model, will cut the memory requirement by 4x, but it is known that the model will be much slower to run than the native f16 - bitsandbytes-fp4: Bitsandbytes 4bit. nf4 should be preferred in most cases but maybe this one has better perplexity performance for you model + - fp8: [BETA] [FP8](https://developer.nvidia.com/blog/nvidia-arm-and-intel-publish-fp8-specification-for-standardization-as-an-interchange-format-for-ai/) (e4m3) works on H100 and above This dtype has native ops should be the fastest if available. This is currently not the fastest because of local unpacking + padding to satisfy matrix multiplication limitations ``` ## SPECULATE