How to map a API function in backend in C++ into frontend in Python? [Questions] (4)
Problem on tune_relay_x86.py [Questions] (3)
Few question regarding autotvm and tune_relay_x86 [Questions] (6)
Error when run pynq-z1 test [Uncategorized] (19)
RK3399 android rpc file [Uncategorized] (1)
[TOPI] How to map our own instrcution set to the operator library? [Questions] (1)
Why mali gpu is slower than arm cpu? [Uncategorized] (4)
How can I build TVM in Windows? [Questions] (3)
End-to-end (TVM+VTA) flow tutorial with Yolo v3 [Uncategorized] (14)
How can i do AutoTVM once for a operator but apply the best config for other input/output shape with best performance? [Questions] (4)
Any documentation on winograd convolution scheduling on CUDA? [Questions] (2)
[Quantization][AutoTVM] Performance degradation of Quantization + AutoTVM vs FP on x86 [Troubleshooting] (10)
Windows build : ambiguous symbols [Uncategorized] (2)
[Quantization] Which operators are quantized in TVM? [Questions] (4)
How can i autotune for more ops? [Uncategorized] (1)
Anyone who knows how to set compile target for Jetson Nano? [Questions] (1)
Hybrid Inter-function call wrong [Uncategorized] (4)
Add new ops for relay.frontend.from_onnx.py [Questions] (4)
[Relay][split] Don't know how to handle type 'tvm.relay.expr.TupleWrapper' [Questions] (5)
[Relay][op] How to understand GetValidCountRel? [Development] (1)
[Relay][concatenate]Downcast from relay.RefType to relay.TensorType failed." [Development] (8)
Python debugger segfaults with tvm [Questions] (8)
[SOLVED] Auto-tuning CUDA: Poor Performance [Questions] (1)
Error when importing TensorFlow models [Troubleshooting] (3)
TVMError: Check failed: *pval >= 0 (-1 vs. 0) : Cannot allocate memory for tensor with negative shape-1 [Uncategorized] (2)
Auto-tuning with Relay: RPC Tracker Error [Troubleshooting] (1)
Deploy the model using Python API and C++ API takes almost the same time? [Uncategorized] (1)
Keras Softmax axis=1 bug [Uncategorized] (1)
[Relay][Expr] how can I swap inputs' data's column in relay? [Questions] (1)
How can we run TVM without pynq-specific cma library? [Questions] (1)