From 2491cc928dd9128a8113dbb34a373756f8c2e37b Mon Sep 17 00:00:00 2001
From: Zachary Streeter <90640993+zstreet87@users.noreply.github.com>
Date: Tue, 11 Feb 2025 13:03:08 -0600
Subject: [PATCH] add deepseek-v3 amd docker command (#3495)

---
 docs/references/{amd_configure.md => amd.md} | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
 rename docs/references/{amd_configure.md => amd.md} (89%)

diff --git a/docs/references/amd_configure.md b/docs/references/amd.md
similarity index 89%
rename from docs/references/amd_configure.md
rename to docs/references/amd.md
index 15c15c625..da41c668d 100644
--- a/docs/references/amd_configure.md
+++ b/docs/references/amd.md
@@ -98,3 +98,21 @@ drun sglang_image \
 ```
 
 With your AMD system properly configured and SGLang installed, you can now fully leverage AMD hardware to power SGLang’s machine learning capabilities.
+
+## Running DeepSeek-V3
+
+The only difference in running DeepSeek-V3 is when starting the server.
+
+```bash
+drun -p 30000:30000 \
+    -v ~/.cache/huggingface:/root/.cache/huggingface \
+    --ipc=host \
+    --env "HF_TOKEN=<secret>" \
+    sglang_image \
+    python3 -m sglang.launch_server \
+    --model deepseek-ai/DeepSeek-V3 # <- here \
+    --tp 8 \
+    --trust-remote-code \
+    --host 0.0.0.0 \
+    --port 30000
+```