Open kalle07 opened 10 months ago
try to rebuild my tensor
Exporting SDXL_juggernautXL_version6Rundiffusion to TensorRT {'sample': [(2, 4, 85, 128), (2, 4, 85, 128), (2, 4, 85, 128)], 'timesteps': [(2,), (2,), (2,)], 'encoder_hidden_states': [(2, 77, 2048), (2, 77, 2048), (2, 77, 2048)], 'y': [(2, 2816), (2, 2816), (2, 2816)]} Building TensorRT engine... This can take a while, please check the progress in the terminal. Building TensorRT engine for D:\stable-diffusion\webui\models\Unet-onnx\SDXL_juggernautXL_version6Rundiffusion_7d723a7b.onnx: D:\stable-diffusion\webui\models\Unet-trt\SDXL_juggernautXL_version6Rundiffusion_7d723a7b_cc89_sample=2x4x85x128-timesteps=2-encoder_hidden_states=2x77x2048-y=2x2816.trt [I] Loading tactic timing cache from D:\stable-diffusion\webui\extensions\Stable-Diffusion-WebUI-TensorRT\timing_caches\timing_cache_win_cc89.cache [I] Building engine with configuration: Flags | [FP16, REFIT, TF32] Engine Capability | EngineCapability.DEFAULT Memory Pools | [WORKSPACE: 16379.50 MiB, TACTIC_DRAM: 16379.50 MiB] Tactic Sources | [CUBLAS, CUDNN, EDGE_MASK_CONVOLUTIONS, JIT_CONVOLUTIONS] Profiling Verbosity | ProfilingVerbosity.LAYER_NAMES_ONLY Preview Features | [FASTER_DYNAMIC_SHAPES_0805, DISABLE_EXTERNAL_TACTIC_SOURCES_FOR_CORE_0805] Building engine: 100%|███████████████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 7.80it/s] [E] 4: [graphShapeAnalyzer.cpp::nvinfer1::builder::`anonymous-namespace'::ShapeAnalyzerImpl::processCheck::867] Error Code 4: Internal Error (/Concat_4: axis 2 dimensions must be equal for concatenation on axis 1.) [!] Invalid Engine. Please ensure the engine was built correctly ERROR:root:Failed to build engine: Invalid Engine. Please ensure the engine was built correctly
try to rebuild my tensor
Exporting SDXL_juggernautXL_version6Rundiffusion to TensorRT {'sample': [(2, 4, 85, 128), (2, 4, 85, 128), (2, 4, 85, 128)], 'timesteps': [(2,), (2,), (2,)], 'encoder_hidden_states': [(2, 77, 2048), (2, 77, 2048), (2, 77, 2048)], 'y': [(2, 2816), (2, 2816), (2, 2816)]} Building TensorRT engine... This can take a while, please check the progress in the terminal. Building TensorRT engine for D:\stable-diffusion\webui\models\Unet-onnx\SDXL_juggernautXL_version6Rundiffusion_7d723a7b.onnx: D:\stable-diffusion\webui\models\Unet-trt\SDXL_juggernautXL_version6Rundiffusion_7d723a7b_cc89_sample=2x4x85x128-timesteps=2-encoder_hidden_states=2x77x2048-y=2x2816.trt [I] Loading tactic timing cache from D:\stable-diffusion\webui\extensions\Stable-Diffusion-WebUI-TensorRT\timing_caches\timing_cache_win_cc89.cache [I] Building engine with configuration: Flags | [FP16, REFIT, TF32] Engine Capability | EngineCapability.DEFAULT Memory Pools | [WORKSPACE: 16379.50 MiB, TACTIC_DRAM: 16379.50 MiB] Tactic Sources | [CUBLAS, CUDNN, EDGE_MASK_CONVOLUTIONS, JIT_CONVOLUTIONS] Profiling Verbosity | ProfilingVerbosity.LAYER_NAMES_ONLY Preview Features | [FASTER_DYNAMIC_SHAPES_0805, DISABLE_EXTERNAL_TACTIC_SOURCES_FOR_CORE_0805] Building engine: 100%|███████████████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 7.80it/s] [E] 4: [graphShapeAnalyzer.cpp::nvinfer1::builder::`anonymous-namespace'::ShapeAnalyzerImpl::processCheck::867] Error Code 4: Internal Error (/Concat_4: axis 2 dimensions must be equal for concatenation on axis 1.) [!] Invalid Engine. Please ensure the engine was built correctly ERROR:root:Failed to build engine: Invalid Engine. Please ensure the engine was built correctly