|
Can I get a inference time layer by layer?
|
|
6
|
1196
|
October 12, 2023
|
|
[CODEGEN]About custom the c code
|
|
0
|
250
|
October 12, 2023
|
|
[Questions] TVMScript sch.tensorize error when codegen CUDA code using Tensor Core
|
|
5
|
465
|
October 12, 2023
|
|
C++ Inference is Twice as Slow as Python in TVM 0.6.1
|
|
4
|
339
|
October 12, 2023
|
|
How to solve this problem?
|
|
0
|
333
|
October 11, 2023
|
|
Not able to build tvm using visual studio
|
|
1
|
580
|
October 11, 2023
|
|
Why does order of patterns matter while appending them to pattern list for MergeComposite pass
|
|
2
|
283
|
October 11, 2023
|
|
[Unity] Open Dev Meeting Oct 10, 2023
|
|
0
|
327
|
October 9, 2023
|
|
Running Stable Diffusion fully in browser with WebGPU with TVM Unity
|
|
6
|
3107
|
October 9, 2023
|
|
[Error] Float16 for Cuda with Autotvm
|
|
5
|
951
|
October 9, 2023
|
|
Relay.build时，conv2d_nchw.cuda报错
|
|
0
|
257
|
October 8, 2023
|
|
Transform custom cuda op in pytorch model to Relay IR
|
|
4
|
603
|
October 8, 2023
|
|
How to use my cuda op implementation in TVM?
|
|
0
|
297
|
August 23, 2023
|
|
Can an operator have more than one target?
|
|
0
|
268
|
October 8, 2023
|
|
Errors while compiling certain ONNXv7 models with tvm
|
|
1
|
369
|
October 6, 2023
|
|
[TIR] Negative or zero extent in for loop
|
|
0
|
379
|
October 5, 2023
|
|
[USMP][UMA] Pin buffer in "main" to a specific memory pool
|
|
2
|
533
|
October 5, 2023
|
|
How to deploy onnx model with QDQ quantization information using TVM?
|
|
1
|
1676
|
October 5, 2023
|
|
[Unity] Open Dev Meeting Oct 3th, 2023
|
|
1
|
277
|
October 4, 2023
|
|
Obtaning the compute graph
|
|
2
|
258
|
October 4, 2023
|
|
Is it possible to get source of compute graph?
|
|
1
|
322
|
October 4, 2023
|
|
What are the versions to use to develop zephyr based project?
|
|
0
|
303
|
October 4, 2023
|
|
Critical Compilation Warning in Generated Model for CMSIS Target
|
|
0
|
404
|
October 2, 2023
|
|
TVM Monthly - September 2023
|
|
0
|
495
|
October 2, 2023
|
|
Running Mobilenet network with UMA Vanilla Accelerator example results in exception: schedule_injective not registered for 'vanilla_accelerator'
|
|
0
|
358
|
October 1, 2023
|
|
Getting "TVMError: cannot make uint from negative value -4" when scheduling TVM programs
|
|
0
|
263
|
September 30, 2023
|
|
Can someone explain how TVM optimizes models for different hardware, and what steps I should take if I want to make TVM support DSA chips?
|
|
1
|
534
|
September 27, 2023
|
|
RFC: Relax - Static Memory Planning and Discontiguous Tensors
|
|
5
|
936
|
September 26, 2023
|
|
[DISCUSS] TVM Community Strategy for Foundational Models
|
|
8
|
2553
|
September 26, 2023
|
|
Better memory planning for relax?
|
|
3
|
670
|
September 26, 2023
|
