[AMD] Support eplb for moriep (#22985)
Co-authored-by: HAI <hixiao@gmail.com>
This commit is contained in:
@@ -58,6 +58,11 @@ SGLang supports various environment variables that can be used to configure its
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>The interval of passes to collect the metric of selected count of physical experts on each layer and GPU rank. 0 means disabled.</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>0</code></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_EPLB_ROCM_P2P_BATCH_CHUNK_SIZE</code></td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Number of logical expert IDs per batch when submitting P2P ops during EPLB rebalance on ROCm. Smaller values prevent RCCL GPU-side accumulation hangs but increase overhead.</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>32</code></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_FORWARD_UNKNOWN_TOOLS</code></td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Forward unknown tool calls to clients instead of dropping them</td>
|
||||
|
||||
Reference in New Issue
Block a user