Uncategorized

Model performance is much slower on Android Device using Java API, ComparedToRunEvaluator (3)

Relay Alter OP Layout Pass Regression (10)

[Resolved] Kernel version mismatch (6)

AutoTVM + Relay tutorials broken? (6)

AutoTVM error when loading ONNX model and invoking NNVM compiler (5)

Dependence decorate and Pillow package (3)

LSTM CPU version (1)

CL_INVALID_WORK_GROUP_SIZE error after auto-tuning for OpenCL on Android Device (11)

Question about TVMOpParam.flatten_data (1)

No OpenCL platform matched given existing options (8)

How can I supply pre-compiled cl kernels to TVM? (3)

How does the C++ API work (and is there a mistake in the example?) (5)

Auto-TVM failed on Android Device, with error msg of "Do not know how to handle return type code 113" (2)

How to load OpenCL kernels when using runtime api for C++ (2)

Fusing conv-act-pooling (2)

Show unflattened tensor in tvm.lower() (5)

Choice about IR, SSA or ANF? (6)

Using external lib (cuDNN) with INT8 ops (4)

[AutoTVM] Fail when search on Rasp Pi3 (2)

How to build a VTA quantized model like the ResNet tutorial? (2)

What does "topi.nn.conv2d_alter_layout" do? (4)

[SOLVED]Run get_start.py error (3)

ONNX error when compiling with nnvm (10)

Having problems running benchmark on raspi (4)

[app][bundle_deploy]when I use bundle_deploy occur error: (1)

Any plan to support 'pip install tvm' (1)

Does TVM use NPU on Kirin970 chip? (3)

Error when run pynq-z1 test (8)

How to profile speed in each layer with RPC? (1)

Reorder stages in tvm (1)