From 7348d9627e5982e78d57fb1c3786d153d927877b Mon Sep 17 00:00:00 2001 From: Yineng Zhang Date: Thu, 6 Feb 2025 16:54:40 +0800 Subject: [PATCH] add AMD guide for DeepSeek-R1 (#3338) --- benchmark/deepseek_v3/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/benchmark/deepseek_v3/README.md b/benchmark/deepseek_v3/README.md index 387a6629f..bb25854be 100644 --- a/benchmark/deepseek_v3/README.md +++ b/benchmark/deepseek_v3/README.md @@ -11,6 +11,8 @@ For optimizations made on the DeepSeek series models regarding SGLang, please re If you do not have GPUs with large enough memory, please try multi-node tensor parallelism. There is an example serving with [2 H20 nodes](https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3#example-serving-with-2-h208) below. +For running on AMD MI300X, use this as a reference. [Running DeepSeek-R1 on a single NDv5 MI300X VM](https://techcommunity.microsoft.com/blog/azurehighperformancecomputingblog/running-deepseek-r1-on-a-single-ndv5-mi300x-vm/4372726) + ## Installation & Launch If you encounter errors when starting the server, ensure the weights have finished downloading. It's recommended to download them beforehand or restart multiple times until all weights are downloaded.