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

Enable MoE deferred finalize by default and drop its expert_weights dtype workaround (#33618)

Browse Source 
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Khoa Pham
2026-08-05 17:56:47 -07:00
committed by GitHub
co-authored by Claude Opus 5
parent c9506d023f
commit beabc5949b
4 changed files with 6 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/references/environment_variables.mdx
+1 -1
View File
@@ -354,7 +354,7 @@ SGLang supports various environment variables that can be used to configure its
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_ENABLE_MOE_DEFERRED_FINALIZE</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Defer the MoE finalize step to overlap it with other work.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>false</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>true</code></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_PATCH_TOKENIZER</code></td>