Qwen25vl ViT Runner#

class Qwen25VLViTRunner : public trt_edgellm::rt::QwenViTRunner#

Qwen2.5-VL vision encoder. Extends the Qwen2-VL base with WINDOW ATTENTION and fps-scaled video MRoPE (tokens_per_second); 2D resize, incrementing pad — all inherited. Mirror of HF modeling_qwen2_5_vl.py.

Public Functions

QwenViTRunner(
std::string const &engineDir,
int32_t llmMaxBatchSize,
int32_t llmMaxSequenceLength,
cudaStream_t stream,
)#

Constructor for QwenViTRunner.

Parameters:

  • engineDir – [in] Directory containing the TensorRT engine files

  • llmMaxBatchSize – [in] Maximum batch size from LLM engine

  • llmMaxSequenceLength – [in] Maximum sequence length from LLM engine

  • stream – [in] CUDA stream for execution

Throws:

  • std::runtime_error – if engine directory does not contain engine files, or if buffer allocation fails

  • json::type_error – if JSON configuration contains unexpected datatypes