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

docs: add DeepSeek V4 FP4 indexer usage (#27035)

Browse Source 
Co-authored-by: Jinyan Chen <jinyanc@nvidia.com>
This commit is contained in:
Jinyan Chen
2026-06-04 00:44:21 -07:00
committed by GitHub
co-authored by Jinyan Chen
parent ff93a576e5
commit 10b6b45cad
2 changed files with 18 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/advanced_features/server_arguments.mdx
+6
View File
@@ -1218,6 +1218,12 @@ Please consult the documentation below and [server_args.py](https://github.com/s
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`sgl-kernel`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>sgl-kernel</code>, <code>torch</code>, <code>flashinfer</code></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--enable-deepseek-v4-fp4-indexer`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Enable the experimental FP4 C4 indexer path for DeepSeek V4. When unset, SGLang keeps the default DeepSeek V4 indexer path. Requires SM100 GPUs with DeepGEMM FP4 indexer support.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`False`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>bool flag (set to enable)</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--fp8-gemm-backend`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Choose the runner backend for Blockwise FP8 GEMM operations. Options: 'auto' (default, auto-selects based on hardware), 'deep_gemm' (JIT-compiled; enabled by default on NVIDIA Hopper (SM90) and Blackwell (SM100) when DeepGEMM is installed), 'flashinfer_trtllm' (FlashInfer TRTLLM backend; SM100/SM103 only), 'flashinfer_cutlass' (FlashInfer CUTLASS backend, SM120 only), 'flashinfer_deepgemm' (Hopper SM90 only, uses swapAB optimization for small M dimensions in decoding), 'cutlass' (optimal for Hopper/Blackwell GPUs and high-throughput), 'triton' (fallback, widely compatible), 'aiter' (ROCm only).</td>