minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

[FlashInfer v0.6.12] Support FlashInfer 4over6 NVFP4 (#25239)

Browse Source
This commit is contained in:
Ziang Li
2026-06-04 14:35:07 -07:00
committed by GitHub
parent 5bf90ad988
commit 4cfebbb95f
3 changed files with 21 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/references/environment_variables.mdx
+10
View File
@@ -574,6 +574,16 @@ SGLang supports various environment variables that can be used to configure its
<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>FLASHINFER_NVFP4_4OVER6</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Enable FlashInfer NVFP4 4over6 scaling for the per-token activation path; effective only with <code>SGLANG_FLASHINFER_NVFP4_PER_TOKEN_ACTIVATION</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>FLASHINFER_NVFP4_4OVER6_E4M3_USE_256</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Use <code>256</code> as the E4M3 scale maximum for FlashInfer NVFP4 4over6 per-token activation scaling; otherwise uses <code>448</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>