|
Cross Compile for Nano with different Tensorrt
|
|
0
|
276
|
March 7, 2024
|
|
Indirect Tensors and Efficient Padding
|
|
0
|
284
|
March 4, 2024
|
|
Support nop function on graph_executor.c
|
|
0
|
341
|
March 3, 2024
|
|
Tvm\src\node\reflection.cc:109: AttributeError: Op object has no attributed span
|
|
0
|
491
|
March 2, 2024
|
|
Need help on Hexagon HVX Optimization
|
|
7
|
1314
|
February 29, 2024
|
|
The impilcation of backend optimization
|
|
1
|
317
|
February 27, 2024
|
|
[TOPI]How to update attrs of ComputeOp on the python side?
|
|
1
|
404
|
February 26, 2024
|
|
End-to-End flow using TIR MetaSchedule and uTVM
|
|
6
|
1235
|
February 23, 2024
|
|
In TVM, do we have to manually specify a schedule?
|
|
10
|
2099
|
February 22, 2024
|
|
Pass_fds not supported on Windows
|
|
0
|
379
|
February 21, 2024
|
|
How to use PAPI to measure FLOPs of a model compiled by TVM?
|
|
4
|
1714
|
February 19, 2024
|
|
How to avoid an op from being fused?
|
|
6
|
979
|
February 19, 2024
|
|
Auto Tuning with Android, Vulkan is not working
|
|
1
|
378
|
February 17, 2024
|
|
[Relax] cross-layer-oiptimizations
|
|
3
|
519
|
February 16, 2024
|
|
TVM transform passes speed issues
|
|
3
|
466
|
February 15, 2024
|
|
[MetaSchedule] How to resume tuning?
|
|
3
|
952
|
February 14, 2024
|
|
Error about relay.nn.conv2d: Entry function uses too much shared data
|
|
0
|
423
|
February 13, 2024
|
|
How to reduce store instrcutions
|
|
0
|
434
|
February 8, 2024
|
|
Extracting a model library in TVM-Unity
|
|
2
|
847
|
February 6, 2024
|
|
TVM contributions starting point
|
|
0
|
353
|
February 4, 2024
|
|
Merge Composites
|
|
0
|
353
|
February 4, 2024
|
|
Error while building cpptest through Visual Studio 16 2019
|
|
2
|
447
|
February 3, 2024
|
|
LLVM cpu features i.e -mattr
|
|
0
|
756
|
February 2, 2024
|
|
How to check annotation value (knob) in auto-tuning process
|
|
1
|
266
|
February 1, 2024
|
|
Question about [Unity] tag in PR title
|
|
2
|
303
|
February 1, 2024
|
|
hifiGAN Inference speed with tvm optimized slower than onnxruntime
|
|
1
|
989
|
February 1, 2024
|
|
Information on Reduce-Branching-Through-Overcompute pass and how to extend the pass if needed
|
|
0
|
274
|
January 31, 2024
|
|
[MetaSchedule] Tricks to Improve Codegen Performance for Conv2D Ops
|
|
0
|
280
|
January 31, 2024
|
|
[VM] VM compile
|
|
0
|
279
|
January 30, 2024
|
|
Composable TIR intrinsics with optional bias?
|
|
0
|
228
|
January 29, 2024
|
