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

Add Ling-3.0-flash-VL cookbook (#38434)

Browse Source
This commit is contained in:
Xinyuan Tong
2026-09-08 23:00:24 +08:00
committed by GitHub
parent 325ab245a1
commit 482e9f257b
8 changed files with 628 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/supported-models/multimodal_language_models.mdx
+5
View File
@@ -301,6 +301,11 @@ SGLang supports video input for Vision-Language Models (VLMs), enabling temporal
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>Qwen/Qwen3-VL-235B-A22B-Instruct</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>The processor gathers <code>video_data</code>, runs Qwen's frame sampler, and merges the resulting features with text tokens before inference.</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><strong>Ling-VL</strong> (Ling-3.0-flash-VL)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>inclusionAI/Ling-3.0-flash-VL</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>InclusionAI's KDA/MLA hybrid MoE VLM (125B total / ~5.1B active) built on the Ling-3.0-flash backbone with a Qwen3-ViT-family vision tower. Image and video inputs are expanded by the Bailing processor with centered mRoPE positions. Requires <code>--trust-remote-code</code>. Audio is not supported.</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><strong>GLM-4v</strong> (4.5V, 4.1V, MOE)</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>zai-org/GLM-4.5V</code></td>