minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[AMD] Document Mori XGMI for Single-Node PD Disaggregation (#25094)

Browse Source 
Co-authored-by: clintg6 <7388379+clintg6@users.noreply.github.com>
This commit is contained in:
Clint
2026-06-18 19:25:49 -07:00
committed by GitHub
co-authored by clintg6
parent d962d18f15
commit fac11f3bc1
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/references/environment_variables.mdx
+5
View File
@@ -365,6 +365,11 @@ SGLang supports various environment variables that can be used to configure its
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Use FP8 for combine</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>"false"</code></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>MORI_DISABLE_AUTO_XGMI</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Set to <code>0</code> to allow Mori to automatically use XGMI for same-node PD disaggregation when no active RDMA device is available.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>unset</code></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_MORI_NUM_MAX_DISPATCH_TOKENS_PER_RANK</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Maximum number of dispatch tokens per rank for MORI-EP buffer allocation</td>