About the Development category
Symbol visibility, linking and double loading
Refine Relay with AutoTVM tutorial
Rewrite simplify rules limited to index type vars
Simplify USE_CUBLAS in config.cmake
Support for evolving tensorflow/ONNX graphs with Relay API
FP16 is slower than FP32 in TVM?
[Relay][Frontend][ONNX] operator support: ConstantOfShape
Jenkins git issue - corrupt repository
Why is cache_write not supported with HybridOp/ExternOp?
Why no constant(immediate) tensor in TVM IR?
[codegen_cuda] How to write a unittest for my PR?
How to create a new operator in TVM
Whether TVM supports the frontend conversion to FLOAT16
[TVM IR] How to get the lhs IR representation?
How to support tf.TensorArray()
Is switching to C++14 considered?
Getting started with the VTA Chisel backend
Whether TVM will support dynamic shapes in the future
TVMError: Check failed: type_code_ == kDLInt (2 vs. 0) : expected int but get float
Use block data format for whole model
[Discussion] Adding a function to Relay module automatically triggers InferType
[Relay][op] How to understand GetValidCountRel?
[Relay][concatenate]Downcast from relay.RefType to relay.TensorType failed."
[IR] Have we used prefetch in our schedule?
How to register FTVMSchedule for new relay op
Explore Optimizations for Concat
[Relay][Concatenate] Missing shape checking for non-concat axes
Request for invite to the slack channel
Disable assert in runtime
next page →