[MM][CG] Support ViT CUDA Graph for Gemma-4 (#46837)

Signed-off-by: Anthony Su <xsuanthony@gmail.com>
Co-authored-by: Linkun Chen <github@lkchen.net>
This commit is contained in:
anthonsu
2026-07-25 15:02:09 -05:00
committed by GitHub
co-authored by Linkun Chen
parent ee1d996367
commit 70009fb934
4 changed files with 476 additions and 1 deletions
+1
View File
@@ -129,6 +129,7 @@ Models opt-in to encoder CUDA Graphs by implementing the [SupportsEncoderCudaGra
| `DeepseekOCRForCausalLM` | `DeepSeek-OCR` | ✅︎ | ❌︎ | ✅︎ |
| `Gemma3ForConditionalGeneration` | `Gemma3` | ✅︎ | ❌︎ | ❌︎ |
| `Glm4vForConditionalGeneration` | `GLM-4.1V, GLM-4.6V-Flash` | ✅︎ | ✅︎ | ❌︎ |
| `Gemma4ForConditionalGeneration` | `Gemma-4` | ✅︎ | ✅︎ | ❌︎ |
| `InternVLChatModel` | `InternVL3.5`, `InternVL3`, `InternVL2.5`, `InternVL2` | ✅︎ | ✅︎ | ❌︎ |
| `KimiVLForConditionalGeneration` | `Kimi-VL` | ✅︎ | ❌︎ | ❌︎ |
| `Llama4ForConditionalGeneration` | `Llama 4` | ✅︎ | ❌︎ | ❌︎ |