iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Document Qwen3.6 (dense + MoE) ViT CUDA graph support (#44720)

Browse Source 
Signed-off-by: harsha20032020 <nhvardhan2020@gmail.com>
This commit is contained in:
Nemani Harsha Vardhan
2026-06-24 14:35:08 +00:00
committed by GitHub
parent 61ee183d28
commit 7dc036058b
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/design/cuda_graphs_multimodal.md
+2 -1
View File
@@ -134,7 +134,8 @@ Models opt-in to encoder CUDA Graphs by implementing the [SupportsEncoderCudaGra
| `Qwen2VLForConditionalGeneration` | `Qwen2-VL` | ✅︎ | ✅︎ | ❌︎ |
| `Qwen2_5_VLForConditionalGeneration` | `Qwen2.5-VL` | ✅︎ | ✅︎ | ❌︎ |
| `Qwen3VLForConditionalGeneration` | `Qwen3-VL` | ✅︎ | ✅︎ | ❌︎ |
| `Qwen3_5ForConditionalGeneration` | `Qwen3.5` | ✅︎ | ✅︎ | ❌︎ |
| `Qwen3_5ForConditionalGeneration` | `Qwen3.5`, `Qwen3.6` | ✅︎ | ✅︎ | ❌︎ |
| `Qwen3_5MoeForConditionalGeneration` | `Qwen3.5-MoE`, `Qwen3.6-MoE` | ✅︎ | ✅︎ | ❌︎ |
| `Step3VLForConditionalGeneration` | `Step3-VL` | ✅︎ | ❌︎ | ❌︎ |
!!! note