[Question][Unity] MetaSchedule tune_tir output
|
|
5
|
1137
|
August 12, 2024
|
Is microTVM still supported?
|
|
4
|
754
|
August 12, 2024
|
Relax:is still under development?whether relax only implements some independent pass optimization?
|
|
1
|
553
|
August 9, 2024
|
Can I use temporary variable(in register) in generated code?
|
|
1
|
645
|
August 9, 2024
|
TVM for random forest/decision tree classifiers
|
|
0
|
237
|
August 9, 2024
|
How to understand graph_json generated by relay.build?
|
|
5
|
1279
|
August 7, 2024
|
Why is tvm.relay.quantize not documented? // Status of quantization in TVM
|
|
0
|
430
|
August 6, 2024
|
Getting block and grid dimensions from CUDA graph
|
|
6
|
1798
|
August 6, 2024
|
Unpack API with Relax
|
|
5
|
770
|
August 6, 2024
|
Dependency Queue
|
|
0
|
263
|
August 6, 2024
|
TVM trains the model like tensorflow1
|
|
0
|
264
|
August 6, 2024
|
Did you forget to bind?
|
|
0
|
437
|
August 5, 2024
|
How to use pinned memory?
|
|
3
|
834
|
August 5, 2024
|
Which parts of TVM should I modify or add for Custom VTA core?
|
|
0
|
288
|
August 2, 2024
|
GEMM core and register file
|
|
0
|
271
|
August 1, 2024
|
TVM installation with precompiled docker image
|
|
0
|
255
|
July 31, 2024
|
Data FLow Architecture in TVM
|
|
1
|
446
|
July 31, 2024
|
Matching one branch of a multi output pattern
|
|
0
|
222
|
July 31, 2024
|
What is the difference between TVMError and InternalError
|
|
1
|
293
|
July 30, 2024
|
Layers are not supported by CUDA backend
|
|
2
|
305
|
July 28, 2024
|
Read block's variable during runtime
|
|
0
|
300
|
July 26, 2024
|
Confused about C/C++ runtimes
|
|
3
|
567
|
July 24, 2024
|
How to compile model to Hexagon?
|
|
3
|
1602
|
July 22, 2024
|
Question about dynamic definition of ShapeExpr
|
|
0
|
314
|
July 19, 2024
|
Is there any plan for supporting pytorch DTensor?
|
|
0
|
318
|
July 19, 2024
|
What target to use? Export compiled target or C code?
|
|
0
|
370
|
July 19, 2024
|
Can cross-compiled TVM models be analyzed using PAPI?
|
|
0
|
244
|
July 19, 2024
|
Is it possible to generate runtime from a relay IRModule without Python?
|
|
1
|
521
|
July 17, 2024
|
Tvm optimizes yolov8 error
|
|
1
|
849
|
July 16, 2024
|
[Question] How TVM run text generation model like gpt2
|
|
28
|
4450
|
July 15, 2024
|