[NVIDIA] Update Minimax-M2.5,M2.7 docs with flags for performance (#24465)
This commit is contained in:
@@ -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 > 1</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`false`</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
Reference in New Issue
Block a user