From 22f2800e804426863c41720ed340de95aa3f8e93 Mon Sep 17 00:00:00 2001 From: Vlad Shulman Date: Wed, 26 Jun 2024 15:47:39 -0700 Subject: [PATCH] Update README.md --- .../fp8_tp2_i4096_o1024_bs30/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama/llama-3-70b-instruct-trt-llm/fp8_tp2_i4096_o1024_bs30/README.md b/llama/llama-3-70b-instruct-trt-llm/fp8_tp2_i4096_o1024_bs30/README.md index 0b7639042..9edb79eb0 100644 --- a/llama/llama-3-70b-instruct-trt-llm/fp8_tp2_i4096_o1024_bs30/README.md +++ b/llama/llama-3-70b-instruct-trt-llm/fp8_tp2_i4096_o1024_bs30/README.md @@ -2,7 +2,7 @@ This is a [Truss](https://truss.baseten.co/) for an FP8 version of LLaMA3-70B-Instruct. Llama is a family of language models released by Meta. This README will walk you through how to deploy this Truss on Baseten to get your own instance of LLaMA3-70B-Instruct. -**Warning: This example is only intended for usage on 4 H100s, changing your resource type for this deployment will result in unsupported behavior** +**Warning: This example is only intended for usage on 2 H100s, changing your resource type for this deployment will result in unsupported behavior** ## Truss