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

Add explicit EPLB balancedness reporting modes (#34998)

Browse Source
This commit is contained in:
Lianmin Zheng
2026-08-16 15:31:11 -07:00
committed by GitHub
parent 77cadf6b98
commit f61f584347
10 changed files with 133 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/advanced_features/server_arguments.mdx
+4 -4
View File
@@ -1885,10 +1885,10 @@ Please consult the documentation below and [server_args.py](https://github.com/s
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Type: int</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--enable-expert-distribution-metrics`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Enable logging metrics for expert balancedness</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`False`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>bool flag (set to enable)</td>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--expert-balancedness-report-mode`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Where to report expert balancedness.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>off</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>off</code>, <code>server_log</code>, <code>prometheus</code>, <code>both</code></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--deepep-config`</td>
docs/docs/hardware-platforms/ascend-npus/reference/support_features.mdx
+3 -3
View File
@@ -1709,9 +1709,9 @@ If the value is int8, you must also set the environment variable:DEEP_NORMAL_MOD
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>A2, A3</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--enable-expert-distribution-metrics`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`False`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>bool flag (set to enable)</td>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--expert-balancedness-report-mode`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>off</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>off</code>, <code>server_log</code>, <code>prometheus</code>, <code>both</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>A2, A3</td>
</tr>
<tr>
docs/docs/references/environment_variables.mdx
+1 -1
View File
@@ -1745,7 +1745,7 @@ SGLang supports various environment variables that can be used to configure its
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_ENABLE_EPLB_BALANCEDNESS_METRIC</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Emit an EPLB balancedness metric.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Removed. Use <code>--expert-balancedness-report-mode=prometheus</code> to emit the EPLB balancedness metric.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>false</code></td>
</tr>
<tr>