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

[diffusion] chore: refresh docs, retire stale knobs, and fix nightly attribution (#34663)

Browse Source
This commit is contained in:
Mick
2026-08-16 15:41:08 +08:00
committed by GitHub
parent a54de989c8
commit 2ee0d38a85
21 changed files with 370 additions and 130 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/sglang-diffusion/compatibility_matrix.mdx
+21 -1
View File
@@ -89,6 +89,12 @@ Rows are grouped when a family shares the same runtime path or optimization supp
<td>T2V, 480p</td>
<td><span className="sgd-muted">No dedicated optimization listed</span></td>
</tr>
<tr>
<td>LingBot Video MoE</td>
<td><div className="sgd-id-list"><code>robbyant/lingbot-video-moe-30b-a3b</code></div></td>
<td>T2V, 480p</td>
<td><span className="sgd-muted">No dedicated optimization listed</span></td>
</tr>
<tr>
<td>Wan2.2</td>
<td><div className="sgd-id-list"><code>Wan-AI/Wan2.2-TI2V-5B-Diffusers</code><code>Wan-AI/Wan2.2-T2V-A14B-Diffusers</code><code>nvidia/Wan2.2-T2V-A14B-Diffusers-NVFP4</code><code>Wan-AI/Wan2.2-I2V-A14B-Diffusers</code></div></td>
@@ -285,6 +291,21 @@ Optimization columns are abbreviated to keep the matrix readable:
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>❌</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>LingBot Video MoE 30B-A3B</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>robbyant/lingbot-video-moe-30b-a3b</code></td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>480p</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>❌</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>FastWan2.2 TI2V 5B</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers</code><br /><code>FastVideo/FastWan2.2-TI2V-5B-Diffusers</code></td>
@@ -678,7 +699,6 @@ Optimization columns are abbreviated to keep the matrix readable:
- `original` keeps official two-stage semantics without the premerged stage-2 transformer path.
- `resident` usually provides the best latency/throughput but uses much more VRAM.
- Default is auto: `resident` on H200/high-memory CUDA GPUs, otherwise `original`.
- Deprecated compatibility: `snapshot` is accepted as an alias for `original` and may be removed after two release cycles.
5. Cosmos3 ships in two sizes — `nvidia/Cosmos3-Nano` (16B) and
`nvidia/Cosmos3-Super` (64B). Both share the same pipeline; the only
difference is transformer depth and width, picked up from