TensorRT-LLMs/docs/source/reference/multimodal-feature-support-matrix.md
Wanli Jiang fc9f4c9295
[TRTLLM-7918][feat] Support kvcache reuse for phi4mm (#7563)
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
2025-09-15 15:47:00 +08:00

1.1 KiB

Multimodal Feature Support Matrix (PyTorch Backend)

Model CUDA Graph Encoder IFB KV Cache Reuse Chunked Prefill
Gemma 3 Yes Yes N/A N/A
HyperCLOVA Yes Yes No No
VILA Yes No No No
LLaVA-NeXT Yes Yes Yes Yes
Llama 4 Yes Yes No No
Mistral-Small-3.1 Yes Yes No No
Phi-4-multimodal Yes Yes Yes No
Qwen2-VL Yes Yes Yes Yes
Qwen2.5-VL Yes Yes Yes Yes