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

Remove deprecated Mamba flags from doc, wrong FP8 GEMM docstrings and change Nemotron image to 0.5.15 (#31094)

Browse Source 
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
This commit is contained in:
Brayden Zhong
2026-07-17 14:34:29 -07:00
committed by GitHub
co-authored by Brayden Zhong
parent c00206c68c
commit 7fc3fb9657
24 changed files with 46 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/advanced_features/quantization.mdx
+2 -2
View File
@@ -248,7 +248,7 @@ Backend selection applies to **blockwise FP8**, **MXFP8** (dense linear), and **
</tr>
<tr>
<td><code>cutlass</code></td>
<td>SM90, SM100/120</td>
<td>SM120</td>
<td>sgl-kernel CUTLASS</td>
</tr>
<tr>
@@ -264,7 +264,7 @@ Backend selection applies to **blockwise FP8**, **MXFP8** (dense linear), and **
</tbody>
</table>
**`auto` selection order:** 1) DeepGEMM (SM90/SM100, installed); 2) FlashInfer TRTLLM (SM100, FlashInfer available); 3) CUTLASS (SM90/SM100/120); 4) AITER (AMD); 5) Triton. **Exception:** SM120 always resolves to Triton.
**`auto` selection order:** 1) DeepGEMM (SM90/SM100, installed); 2) FlashInfer TRTLLM (SM100, FlashInfer available); 3) CUTLASS (SM120); 4) AITER (AMD); 5) Triton (fallback).
**MXFP8 dense linear:** `auto` uses `flashinfer_cutlass` on SM100 (else `triton`). `flashinfer_cutlass` is fastest on most shapes; `flashinfer_trtllm` is faster only at small M.