Welcome to TVM Community [Uncategorized] (1)
Request for ResNet50 ONNX example review [Application] (2)
Dependence decorate and Pillow package [Uncategorized] (1)
Failed to convert gluoncv yolov3 into tvm [Questions] (2)
The ABI compatibility of `PackedFunc` [Development] (12)
[SOLVED] GPU mode is slower than CPU? [Questions] (8)
[VTA&TVM] Questions after investigating resnet.py tutorial [Questions] (3)
Support for Embedding, Bidirectional and others [Questions] (1)
Not able to deploy on arm64-v8a target without RPC [Development] (6)
Some basic questions related to training, qualtization and backends [Questions] (1)
Error when run pynq-z1 test [Uncategorized] (8)
How to profile speed in each layer with RPC? [Uncategorized] (1)
Does TVM use NPU on Kirin970 chip? [Uncategorized] (2)
Reorder stages in tvm [Uncategorized] (1)
Where are the OpenCL kernel sources stored when setting tgt = tvm.target.mali()? [Questions] (2)
Should we use PureExtern for some TVM ops? [Development] (10)
Autotune error with Qualcomm Adreno [Questions] (4)
LLVM error "option ... registered more than once" while loading libtvm.so [Questions] (12)
[BUG] storage rewrite doesn't correctly handle local buffer allocation [Development] (1)
nnvm._base.NNVMError: Cannot find argument 'auto_pad' [Development] (11)
Design problems for Relay to support NLP models [Development] (10)
How does the C++ API work (and is there a mistake in the example?) [Uncategorized] (1)
How to dynamically change schedule based on graph topology [Questions] (1)
Incompatible attr in node elemwise_add0 at 1-th input: expected [1,256], got [256] [Development] (1)
Tuning tflite with auto tuner [Questions] (3)
Model can Import by NNVM but failed on Relay [Uncategorized] (3)
[tvm][arithmetic] Should we use the empty_value as base for ComputeReduce? [Questions] (7)
Sequential model loading error. sym, params = nnvm.frontend.from_keras(model) [Questions] (1)
Compiling option for performance such as '-O2' [Questions] (2)
TVM-VTA Architecture Scope and Roadmap [RFC] (8)