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

[Scheduler] Enable decode retraction ordering under speculative decoding (#32023)

Browse Source
This commit is contained in:
Liangsheng Yin
2026-07-23 00:42:56 -07:00
committed by GitHub
parent a25164bda3
commit 9b853e6832
8 changed files with 71 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/references/environment_variables.mdx
-5
View File
@@ -1679,11 +1679,6 @@ SGLang supports various environment variables that can be used to configure its
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Plan the next step on a separate stream to overlap with the current step (Overlap Spec V2).</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>SGLANG_SPEC_ENABLE_STRICT_FILTER_CHECK</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Enable strict filter checks in speculative decoding.</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_SPEC_SKIP_ZERO_STEP_DRAFT_EXTEND</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Skip draft_extend while adaptive spec is at steps=0; saves a draft forward but the draft KV goes stale.</td>