Welcome to TVM Community [Uncategorized] (2)
Yolov3-Tiny Conversion | Cuda Error | Script inside [Questions] (3)
[AutoTVM] Safety of transformations, KeyError: 'tile_x' [Questions] (2)
Some questions about building tvm on windows [Troubleshooting] (2)
What's the difference between tvm extern and hybrid script? [Questions] (2)
How to determine the input order of tvm's concatenate layer? [Uncategorized] (1)
[ERROR]CUDA compilation error [Questions] (4)
About side effect [Questions] (1)
The implementation mechanism about weight layout transform work [Questions] (3)
Byte alignment of weight layout transform [Questions] (2)
Symbol visibility, linking and double loading [Development] (4)
Autotune Relay Mobile GPU - CUDA_ERROR_INVALID_PTX on Nano and TX2 [Troubleshooting] (4)
Refine Relay with AutoTVM tutorial [Development] (7)
Layout conversion pass [RFC] (4)
Unable to export lib and, save graph and params to a file [Uncategorized] (4)
Wrong output shape and format [Troubleshooting] (1)
Rewrite simplify rules limited to index type vars [Development] (5)
Issue with GPU Autotune script | Cpu working fine [Questions] (5)
[Relay] CUDA_ERROR_INVALID_VALUE occurs when testing conv2d_grad [Questions] (1)
[VTA] Issue with TSIM based simulation of resnet18 inference on VTA [Troubleshooting] (1)
[RFC][VTA] bfloat16/fp8/fp9/posit tensor core [RFC] (1)
Add input preprocess [Questions] (1)
Import Tensorflow graph into Relay (Data format "NHWC" Issue) [Questions] (4)
No speed increase when converting model to TVM [Questions] (13)
Python debugger segfaults with tvm [Questions] (8)
Error "direct host side access to device memory is detected in ... , did you forget to bind?" when compile a onnx model with target cuda ( 2 ) [Questions] (27)
Support of different GPU architectures [Troubleshooting] (5)
Recurrent Neural Network and CRNN support [Questions] (4)
How to extend NNVM/TVM as a static compiler for HW accelerator like NVDLA? [Questions] (8)
[Discussion] New IR pass proposal: CombineParallelDense [RFC] (17)