Apache TVM Discuss

Topic	Replies	Views	Activity
Welcome to Apache TVM Community	0	7350	March 28, 2018
Error Reporting Announcement See https://github.com/apache/incubator-tvm/pull/6274 for current status, hoping to merge soon ™. FOR USERS ENCOUNTERING INTERNAL ERRORS This document is intended to serve as a living document on the error reporting pro…	2	7573	September 4, 2020
[Bug] relax ONNX Resize operator conversion with opset_version=11 is unsupported Troubleshooting	3	59	April 1, 2025
Phasing out Legacy Components Development	39	3472	April 1, 2025
[Release][Docs] Historical documentation related Questions	4	115	March 29, 2025
Can Dynamic Neural Networks run on TVM? Questions	0	37	March 27, 2025
Why doesn't the official tutorial work? Questions	6	114	March 27, 2025
How to tune GNN models in TVM? Questions	0	45	March 27, 2025
Issue with R.reshape() and R.flatten() in Decomposing torch.masked_select Troubleshooting	2	69	March 27, 2025
Segmentation fault when rewrite visit_binding_block in MyPass	4	131	March 27, 2025
Prevent tvm.lower from Flattening the buffers Questions	0	35	March 26, 2025
Why is the constant variables like cse_var_1: T.bool = not T.bool(False) in tir not optimized after tvm.build? cse_var_1 is generated as a function param Questions	0	34	March 26, 2025
[Release] v0.20.0 Release Schedule Announcement	0	63	March 24, 2025
[Relax][ONNX Frontend] Does the Relax frontend support NonMaxSuppression? Questions	1	143	March 21, 2025
How to handle dynamic input shapes in TVM? Questions	2	198	March 17, 2025
How does TVM decide CUDA kernel launch configurations? Development	1	84	March 15, 2025
problem on build target Questions	0	55	March 14, 2025
TVMError: Binary was created using {relax.VMExecutable} but a loader of that name is not registered. Available loaders are relax.Executable, opencl. Perhaps you need to recompile with this runtime enabled Questions	2	119	March 13, 2025
Error when using TVM	1	74	March 12, 2025
Error while Installing TVM from source on Windows Troubleshooting	6	369	March 12, 2025
Any pass can make the address accessed by each thread are continuous Questions	0	49	March 12, 2025
[Relax][Runtime] Difference between runtime/vm and runtime/relax_vm Questions	3	125	March 11, 2025
[Pytorch] Custom Mappings in from_fx vs. from_imported_program and Choosing Between exported_program and fx.Graph for TVM IRModules Questions	0	72	March 11, 2025
[backend codegen] Hexagon Backend codegen Questions	0	75	March 11, 2025
Variable `matmul` is directly accessed by host memory Troubleshooting	2	124	March 11, 2025
About autoTVM Cannot find config for target	0	56	March 11, 2025
Feature Request: Support for Scaled Dot Product in TVM CUDA Backend Tensor Cores for FP8 MatMul Development	2	142	March 9, 2025
Running LegalizeOps in C++ Troubleshooting	2	147	March 8, 2025
TVM pattern for strided_slice2splite? Questions	0	49	March 8, 2025
Does TVM still support bundle_deploy for generating standalone executables in the Relax era? Questions	0	70	March 7, 2025

Welcome to Apache TVM Community

0

7350

March 28, 2018

Error Reporting

See https://github.com/apache/incubator-tvm/pull/6274 for current status, hoping to merge soon ™. FOR USERS ENCOUNTERING INTERNAL ERRORS This document is intended to serve as a living document on the error reporting pro…