|
About the Questions category
|
|
1
|
600
|
July 16, 2018
|
|
TVM and Nvidia TensorRT
|
|
0
|
19
|
May 21, 2022
|
|
CUDA_ERROR_INVALID_PTX when trying to run single conv2d layer after compilation
|
|
3
|
1891
|
May 21, 2022
|
|
Pytorch inference time faster than auto tuning TVM
|
|
1
|
42
|
May 20, 2022
|
|
Tuning unet with auto scheduler is slower than pytorch on Nvidia Devices
|
|
0
|
29
|
May 19, 2022
|
|
Does Auto Schedule support INT8 turning on X86-64 CPU
|
|
5
|
91
|
May 18, 2022
|
|
Could tvm use fp16 to infer?
|
|
15
|
623
|
May 17, 2022
|
|
Split operator in Relay?
|
|
3
|
268
|
May 17, 2022
|
|
Fp16 tvm.relay.transform.ToMixedPrecision
|
|
0
|
30
|
May 16, 2022
|
|
Gdb print any tvm::ObjectPtr's data_ will bad address
|
|
2
|
69
|
May 14, 2022
|
|
[Relay] Create a zero tensor of batch size
|
|
0
|
30
|
May 14, 2022
|
|
Auto scheduler: Can we get the relay function for an extracted task?
|
|
0
|
25
|
May 14, 2022
|
|
Pattern matching has_attr using any value
|
|
1
|
36
|
May 12, 2022
|
|
Auto scheduler Cannot find any valid schedule
|
|
0
|
31
|
May 12, 2022
|
|
May I ask why I can't find the introduction of relay_intergration. Py in the official documentation? I want to know about autotvm.task.extract_from_program
|
|
0
|
30
|
May 12, 2022
|
|
[CMSIS-NN] qnn_max_pool2d layout on cortex M7 without NPU
|
|
7
|
107
|
May 11, 2022
|
|
VTA graph packing
|
|
3
|
122
|
May 11, 2022
|
|
CUDA streams per thread
|
|
1
|
57
|
May 10, 2022
|
|
Question about the implementation of relu6
|
|
1
|
43
|
May 9, 2022
|
|
Any way to dump the cuda host code?
|
|
5
|
75
|
May 9, 2022
|
|
Getting tvm-generated cuda codes
|
|
6
|
542
|
May 7, 2022
|
|
Cross compiling RISC V with spike emulation
|
|
8
|
219
|
May 6, 2022
|
|
[AutoScheduler] Cannot break Sample Init Population loop
|
|
0
|
37
|
May 6, 2022
|
|
How to use function in tvm/src/printer
|
|
2
|
70
|
May 6, 2022
|
|
How to use var to declare match_buffer and alloc_buffer in tvm.script?
|
|
2
|
77
|
May 4, 2022
|
|
Dynamic input/output shapes (batch size)
|
|
4
|
121
|
May 4, 2022
|
|
What does the kernel in tvm compiled to cuda mean?
|
|
4
|
79
|
May 3, 2022
|
|
Tvm Inference peformance almost 10x better than pytorch
|
|
9
|
216
|
May 2, 2022
|
|
[ Bug ] The arm cpu performance of the new version of tvm is too low than the old version
|
|
1
|
326
|
May 1, 2022
|
|
Have anyone deployed rpc tracker to k8s cluster?
|
|
4
|
89
|
April 28, 2022
|
