C Code Generation Examples (2)
Time is longer by using relay.quantize (3)
How to schedule several layers with association in autotvm (4)
[SOLVED] Autotuning with different Tuners - performance related question (3)
Problem about generating matrix multiply CUDA code (4)
[ONNX][Relay] Inconsistency between Int32 and Int64 after .view() opeartion (3)
Problem is running iOS sample (5)
Bind reduce axis to blocks (5)
What is the difference between tvm.var and tvm.relay.var? (4)
Problem in create tvm const (1)
C code generator (9)
[app][bundle_deploy] got segmentation fault (3)
DNN Model Splitting through TVM (1)
If we need to support PHI node for SSA? (1)
Mixed mode debug of Python/C++? (1)
[AutoTuning] How to debug when all trials are failing on GPU (2)
How to load .params file in java? (2)
[AutoTVM] Cannot get local GPU in offline environment (4)
Test about LowerStorageAccessInfo (1)
Add two operators to support TFLite SSD Mobilenet models (5)
How can we pass tuple inputs to a Relay function? (4)
About computational graph (3)
[AutoTVM] can not build dynamic and system-lib from the best history record simultaneously (3)
Select and if_then_else (2)
[SOLVED] After clean built 'tvm._ffi._ctypes.node.NodeBase' object has no attribute 'set_default' (11)
Problem with trying to tensorize ROI Pooling (1)
TFLite Mobilenet model on intel_graphics - Incompatible broadcast dims (3)
Can not compile quantized TFLite model with INT32 bias (3)
Fail to run docker pre-build image (1)
I didn't get the performence difference under 'cpu' or 'vulkan' or 'opencl' mode, i didin't know what's wrong, any helps, thanks (2)