About the Development category (1)
The ABI compatibility of `PackedFunc` (12)
Not able to deploy on arm64-v8a target without RPC (6)
Should we use PureExtern for some TVM ops? (10)
[BUG] storage rewrite doesn't correctly handle local buffer allocation (1)
nnvm._base.NNVMError: Cannot find argument 'auto_pad' (11)
Design problems for Relay to support NLP models (10)
Incompatible attr in node elemwise_add0 at 1-th input: expected [1,256], got [256] (1)
[SOLVED] Excute ./ in howto_deploy directoy problem (3)
[Solved] Recreate the super_resolution.onnx neural network graph using nnvm (1)
[RELAY] custom arithmetic types (bfloat8, posit<nbits,es>, etc.) (2)
"Unresolved intrinsic floor with return type int32" (2)
Functional, architecture, performance simulation for VTA (1)
tvm.ir_pass.IRTransform doesn't recurse when pre_order makes a change (3)
[RELAY] Injective ops do not work with tuple (8)
[Bug] CoreML frontend fails on NNVM with opt_level=3 and target=CUDA (1)
Compile failure after successfull auto-tune (2)
MXNet SSD Model Compiled to TVM SSD Model (6)
[Codegen][CUDA] Bug in global barrier (13)
[Hybrid] variables on CUDA should have 'local' scope (1)
[SOLVED][Relay] Global reduce fails to compile (4)
[Solved][Relay] Flaky compilation behavior (3)
Is there anything like "unlikely"? (2)
[Code Base] Understanding schedule.normalize() (1)
Flaky Test Cases Thread (2)
Cache_write does not replace vars in reducer identity (3)
tensorflow::ops::AddN is not supported (2)
Reason (and alternatives) for some min/max simplification rules (4)
[TVM Compiler] Performance measurement for TVM compiler pipeline (3)
[Graph IR] Comparison between Relay, NNVM and others (4)