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

Remove retired DSA env paths (#29912)

Browse Source
This commit is contained in:
Baizhou Zhang
2026-07-05 22:58:02 -07:00
committed by GitHub
parent 6f22790943
commit 5eb1b6a7ba
7 changed files with 136 additions and 584 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/references/environment_variables.mdx
-10
View File
@@ -521,16 +521,6 @@ SGLang supports various environment variables that can be used to configure its
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Tie-break mode for FlashInfer DSA topk when <code>--dsa-topk-backend=flashinfer</code>: unset disables explicit tie-breaking, <code>small</code> prefers the smaller candidate index for equal scores, and <code>large</code> prefers the larger candidate index for equal scores. Setting this variable makes FlashInfer use deterministic topk.</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_DSA_ENABLE_MTP_PRECOMPUTE_METADATA</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Precompute metadata that can be shared among different draft steps when MTP is enabled. <code>SGLANG_NSA_ENABLE_MTP_PRECOMPUTE_METADATA</code> is a deprecated alias.</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_USE_FUSED_METADATA_COPY</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Control whether to use fused metadata copy kernel for cuda graph replay</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_DSA_PREFILL_DENSE_ATTN_KV_LEN_THRESHOLD</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>When the maximum kv len in current prefill batch exceeds this value, the sparse mla kernel will be applied, else it falls back to dense MHA implementation. Default to the index topk of model (2048 for DeepSeek V3.2). <code>SGLANG_NSA_PREFILL_DENSE_ATTN_KV_LEN_THRESHOLD</code> is a deprecated alias.</td>