We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 31802de commit e07a970Copy full SHA for e07a970
docs/source/reference/multimodal-feature-support-matrix.md
@@ -0,0 +1,13 @@
1
+# Multimodal Feature Support Matrix (PyTorch Backend)
2
+
3
+| Model | CUDA Graph | IFB w/ SharedTensor | KV Cache Reuse | Chunked Prefill |
4
+| :----------------- | :--------- | :------------------ | :------------- | :-------------- |
5
+| Gemma 3 | Yes | Yes | No | No |
6
+| HyperCLOVA | Yes | Yes | No | No |
7
+| VILA | Yes | No | No | No |
8
+| LLaVA-NeXT | Yes | No | No | No |
9
+| Llama 4 | Yes | No | No | No |
10
+| Mistral | Yes | Yes | No | No |
11
+| Phi-4-multimodal | Yes | Yes | No | No |
12
+| Qwen2-VL | Yes | Yes | Yes | No |
13
+| Qwen2.5-VL | Yes | Yes | Yes | No |
0 commit comments