[MM][CG] Support ViT full CUDA graph for Ernie-4.5-VL image inference (#45254)

Signed-off-by: Qiuyang Yue <yueqiuyang1389@gmail.com>
This commit is contained in:
Qiuyang Yue
2026-08-06 05:04:19 +00:00
committed by GitHub
parent 821717118f
commit 777b01d1a8
4 changed files with 288 additions and 12 deletions
+1
View File
@@ -118,6 +118,7 @@ Models opt-in to encoder CUDA Graphs by implementing the [SupportsEncoderCudaGra
| Architecture | Models | CG for Image | CG for Video | Dual-Path Graph |
| ------------ | ------ | ------------ | ------------ | --------------- |
| `DeepseekOCRForCausalLM` | `DeepSeek-OCR` | ✅︎ | ❌︎ | ✅︎ |
| `Ernie4_5_VLMoeForConditionalGeneration` | `ERNIE-4.5-VL` | ✅︎ | ❌︎ | ❌︎ |
| `Gemma3ForConditionalGeneration` | `Gemma3` | ✅︎ | ❌︎ | ❌︎ |
| `Glm4vForConditionalGeneration` | `GLM-4.1V, GLM-4.6V-Flash` | ✅︎ | ✅︎ | ❌︎ |
| `Gemma4ForConditionalGeneration` | `Gemma-4` | ✅︎ | ✅︎ | ❌︎ |