docs/design/cuda_graphs_multimodal.md · 80118853f42a728805e6a861ffb50f3b876a9939 · OpenDAS / vllm_cscc

[MM][Perf][CG] Support ViT full CUDA graph for Qwen3-VL video inference (#38061) · 80118853

Shanshan Shen authored Apr 14, 2026


Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

80118853

cuda_graphs_multimodal.md 12.5 KB

Replace cuda_graphs_multimodal.md