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

[FlashInfer v0.6.11] [RL] Support FlashInfer per-token NVFP4 MoE (#22918)

Browse Source
This commit is contained in:
Ziang Li
2026-05-19 01:04:48 -07:00
committed by GitHub
parent fbfddfd5c7
commit 78cb38ed5e
6 changed files with 42 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/references/environment_variables.mdx
+5
View File
@@ -549,6 +549,11 @@ 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 nvfp4 for moe dispatch (on flashinfer_cutlass or flashinfer_cutedsl moe runner backend)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>"false"</code></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_FLASHINFER_NVFP4_PER_TOKEN_ACTIVATION</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Enable FlashInfer TRTLLM per-token NVFP4 activation scaling; ignores checkpoint activation FP32 scale by treating it as <code>1</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><code>false</code></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Quantize moe of nextn layer from BF16 to FP8 when launching DeepSeek NVFP4 checkpoint</td>