Welcome to TVM Community (2)
Error_no=1 and error_no=4 (2)
Auto tuning not working on Windows (1)
What can get speedup with Duff's Device? (6)
Autotvm skips depthwise_conv2d_nchw workloads for llvm x86_64 (5)
Expr Simplifier for tvm.var (8)
How to write a custom operator for tvm use? (1)
How to add a similar -g option to compile tvm to generate debugging information (2)
Why do we need to build TVM runtime on remote device for Auto TVM? (11)
Failed to Tune Tensorflow mobilenet_v1 model for x86 (8)
Error when run pynq-z1 test (19)
RK3399 android rpc file (1)
Why mali gpu is slower than arm cpu? (4)
End-to-end (TVM+VTA) flow tutorial with Yolo v3 (14)
Windows build : ambiguous symbols (2)
How can i autotune for more ops? (1)
Hybrid Inter-function call wrong (4)
TVMError: Check failed: *pval >= 0 (-1 vs. 0) : Cannot allocate memory for tensor with negative shape-1 (2)
Deploy the model using Python API and C++ API takes almost the same time? (1)
Keras Softmax axis=1 bug (1)
How to create Operation() for Realize/ProducerConsumer stmt (2)
Do I need full TVM in order to USE_GRAPH_RUNTIME_DEBUG ON? (1)
Lib.export_library cc param was renamed to compile_cmd (1)
Target llvm is not enabled (2)
Tvm 's detection speed is so slower than Mxnet on SSD-Mobilenet (10)
Auto-tuning for Atom CPU gives worse results than untuned model (2)
Where can I find the implementation for OpenCL kernel for MaxPool gradient calculation? (2)
Features.md missing (2)
Winograd variable tile_size knob (8)
Performance regression with relay (opt_level=3) (5)