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

Inference Support Mamba 2 and 1 (#34556)

Browse Source
This commit is contained in:
desmond-intel
2026-09-12 20:51:18 +08:00
committed by GitHub
parent fd32226706
commit 6dc7b3421b
16 changed files with 1544 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/supported-models/generative_models.mdx
+5
View File
@@ -268,6 +268,11 @@ in the GitHub search bar.
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>tiiuae/Falcon-H1-34B-Instruct</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>TII's hybrid Mamba-Transformer architecture combining attention and state-space models for efficient long-context inference.</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><strong>Mamba-Codestral</strong> (7B, Mamba2)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>mistralai/Mamba-Codestral-7B-v0.1</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Mistral AI's pure Mamba2 state-space model for code generation; uses selective state spaces instead of attention, so it holds no KV cache.</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><strong>Hunyuan-Large</strong> (389B, MoE)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>tencent/Tencent-Hunyuan-Large</code></td>