Uncategorized


Welcome to TVM Community (1)
How to tune vulkan target for mobile phones? (9)
How to deploy my model to VTA? (8)
[VTA] Question about Lattice Semiconductor boards (1)
[SOLVED] Can auto-tuner frameworks like Halide/TVM generate high performance reduction algorithm? (3)
AutoTVM tree RNN model (2)
Nnvm quick start error (6)
LLVM error when deploy mobilenet based model on raspberry pi3b (2)
[Solved] Hybrid Frontend Passing Var error (5)
Problem running task_lint.sh locally (6)
[Relay]Similar functionality of graph infer_shape in nnvm (3)
Traverse Function(Graph) in Relay (3)
Question in opt_gemm.py (2)
[AutoTVM] How to assemble multiple logs for tophub (3)
Need a TVM teacher (6)
Tensorize in multithreaded environment (18)
Auto tuning ERROR: relocation R_X86_64_32S against `.rodata.cst16\' can not be used when making a shared object (2)
How to use opencl to speed up yolov3-tiny on rk3399 (2)
[AutoTuning] nnvm.sym.dense config space issue (4)
Error when run pynq-z1 test (7)
Using TVM on an Embedded Platform without an OS? (6)
Error when run apps/howto_deploy (4)
TVM + NNPACK performance on UNet (ARMv7) (3)
How can I view the 'real' assembly of a TVM model, and how exactly does it get called? (2)
Full name of NNVM, TVM (3)
Issue with Pad Op importing ONNX models (2)
Input data for TVM C++ API (4)
【Kernel C code】kernel c code parameter order is not the same with python script while building kernel (3)
Any tips on copying data from cpu to gpu, bottleneck? (9)
Stochastic pooling (1)