[NVIDIA] Update Minimax-M2.5,M2.7 docs with flags for performance (#24465)

This commit is contained in:
Trevor Morris
2026-06-11 14:58:44 -07:00
committed by GitHub
parent fee717f303
commit 0bac184425
3 changed files with 62 additions and 3 deletions
@@ -540,6 +540,11 @@ SGLang supports various environment variables that can be used to configure its
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Use Cutlass FP8 MoE kernel on Blackwell GPUs (deprecated, use --moe-runner-backend=cutlass)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`false`</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_USE_FUSED_PARALLEL_QKNORM</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Use the fused parallel QK RMSNorm kernel for MiniMax-M2.x on CUDA when attention TP size &gt; 1</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`false`</td>
</tr>
</tbody>
</table>