|
Nested parallel loop is not supported by threadpool, try fuse them instead
|
|
0
|
369
|
November 9, 2019
|
|
Very high CPU utilization of TVM inference vs. TensorFlow Lite
|
|
6
|
2378
|
November 9, 2019
|
|
[DISCUSS] Use Object Protocol for Module/NDArray
|
|
5
|
673
|
November 8, 2019
|
|
[TE][CUDA] Issues with high perf GEMM api
|
|
5
|
886
|
November 8, 2019
|
|
How can I achieve the inference time of ”Auto-tuning a convolutional network for x86 CPU“
|
|
0
|
371
|
November 8, 2019
|
|
TVM Monthly - Oct 2019
|
|
0
|
1703
|
November 2, 2019
|
|
What is the difference between relay.build_module.create_executor and relay.build
|
|
0
|
561
|
November 8, 2019
|
|
Pool2D gives bad output for Integer inputs
|
|
6
|
1253
|
November 7, 2019
|
|
TVM deadlocking when calling python PackedFunc from generated code
|
|
4
|
553
|
November 7, 2019
|
|
The purpose of VM：Relay virtual machine?
|
|
3
|
1435
|
November 7, 2019
|
|
CUDA async cudaMemcpyAsync/cudaMallocHost
|
|
1
|
1758
|
November 7, 2019
|
|
Lowering QNN conv2d / tflite
|
|
4
|
1081
|
November 7, 2019
|
|
VTA Conv2d Optimization Schedule and Optimal Throughput
|
|
3
|
812
|
November 7, 2019
|
|
Configurable fusion and heterogeneous execution
|
|
4
|
1022
|
November 7, 2019
|
|
Creating a custom vta bitstream for PYNQ Z1
|
|
3
|
1111
|
November 7, 2019
|
|
[vta] [pynq] [tensorflow] Running TensorFlow models on PYNQ FPGA
|
|
2
|
1264
|
November 7, 2019
|
|
[VTA][FPGA] Running a Tensorflow graph on VTA
|
|
1
|
747
|
November 7, 2019
|
|
[Solved][Python 2 -> 3] relay.build gives error: NoneType' object is not subscriptable
|
|
4
|
2551
|
November 7, 2019
|
|
tensorflow::ops::AddN is not supported
|
|
7
|
1025
|
November 7, 2019
|
|
Missing TFLITE operators in relay
|
|
0
|
351
|
November 7, 2019
|
|
How does TVM support batch>1, while import a tensorflow pb which is frozen as batch=1
|
|
3
|
1106
|
November 7, 2019
|
|
Why vectorize couldn't codegen vfma.f32 instruction on armv7?
|
|
18
|
2452
|
November 7, 2019
|
|
[auto-tune] Does the auto-tune speed become slower with the auto-tuning proceding?
|
|
2
|
479
|
November 7, 2019
|
|
Tvm.compute with variable shape fails to build
|
|
0
|
669
|
November 6, 2019
|
|
TVM nms support?
|
|
0
|
586
|
November 6, 2019
|
|
Tensorflow and TVM gives different results with the same model
|
|
1
|
698
|
November 6, 2019
|
|
[Quantization] Understanding the quantization passes
|
|
2
|
947
|
November 6, 2019
|
|
DepthWise Transposed Conv error
|
|
0
|
723
|
November 6, 2019
|
|
Float16 for Cuda - Performance
|
|
11
|
2644
|
November 6, 2019
|
|
How to speed up int8/int16 computing in arm cpu?
|
|
12
|
4165
|
November 6, 2019
|