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

[NPU] [DOC] clarify Ascend NPU exclusive supported values for speculative args (#26903)

Browse Source
This commit is contained in:
amote-i
2026-06-01 16:40:11 +08:00
committed by GitHub
parent b14fba17d9
commit d078cb72bd
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx
+2 -2
View File
@@ -1346,7 +1346,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--speculative-moe-a2a-`<br/>`backend`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`None`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`ascend_fuseep`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`ascend_fuseep` (the only supported value on Ascend NPU)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>A2, A3</td>
</tr>
<tr>
@@ -1358,7 +1358,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--speculative-draft-model-quantization`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`None`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`unquant`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`unquant` (the only supported value for speculative decoding on Ascend NPU)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>A2, A3</td>
</tr>
</tbody>