|
[SOLVED] TVMC Python for MicroTVM
|
|
3
|
385
|
October 11, 2024
|
|
Batched Inference for LLM
|
|
3
|
337
|
October 7, 2024
|
|
Can TVM generate kernel functions corresponding to the fused operators? how can I obtain the derivative (gradient) of the fused operator?
|
|
1
|
296
|
October 4, 2024
|
|
Does tvm support dynamic input shape?
|
|
24
|
7322
|
September 28, 2024
|
|
RPC connection error
|
|
1
|
676
|
September 27, 2024
|
|
[VTA] DE10 Nano
|
|
0
|
253
|
September 27, 2024
|
|
[HELP!] How to avoid TVM increase the tensor dimensions?
|
|
0
|
254
|
September 25, 2024
|
|
A dynamic link library (DLL) failure after trying to use TVM built from source on Windows
|
|
0
|
444
|
September 22, 2024
|
|
Segmentation fault (core dumped) for ARM intrinsic after tvm.build
|
|
2
|
1036
|
September 20, 2024
|
|
Cannot find tuned schedules for target=cuda -keys=cuda,gpu -arch=sm_86 -max_num_threads=1024 -thread_warp_size=32,
|
|
0
|
319
|
September 12, 2024
|
|
AttributeError: Module has no function '__tvm_main__'
|
|
5
|
1385
|
September 10, 2024
|
|
TVM C++ deployment failed
|
|
1
|
1068
|
September 5, 2024
|
|
[Hexagon] Error opening FastRPC channel
|
|
15
|
4286
|
September 3, 2024
|
|
Multiple VTA instances
|
|
0
|
277
|
September 3, 2024
|
|
Rust module "tvm_graph_rt": can it run on cuda device? can I iterate over its output without copying from gpu to cpu?
|
|
0
|
298
|
August 31, 2024
|
|
Does TVM support multiple streams on gpu?
|
|
2
|
433
|
August 31, 2024
|
|
how do I use dlpackrs with apache TVM for zero-copy?
|
|
0
|
307
|
August 28, 2024
|
|
[rust] how to use dlpackrs to convert tvm's NDArray into Array3<f32> ?
|
|
0
|
222
|
August 28, 2024
|
|
Te.create_prim_func vs tvm.lower
|
|
6
|
509
|
August 26, 2024
|
|
Pipeline Executor with VTA Sim
|
|
0
|
295
|
August 26, 2024
|
|
why VTA only supports 2 virtual threads？
|
|
0
|
298
|
August 23, 2024
|
|
Build Apache TVM runtime for Adreno GPU on Android ARM64v8
|
|
1
|
723
|
August 20, 2024
|
|
Running bench examples on Adreno GPU too slower than benchmark
|
|
0
|
353
|
August 18, 2024
|
|
TVM unroll is different from real code
|
|
0
|
298
|
August 18, 2024
|
|
How are input_scale and input_zero_points set for the qnn layers?
|
|
0
|
292
|
August 14, 2024
|
|
GEMM using OpenCL ML extensions by Qualcomm is slow?
|
|
0
|
462
|
August 14, 2024
|
|
Why excactly nn.batch_norm has a 'TOpPattern' but nn.layer_norm doesn't?
|
|
0
|
279
|
August 14, 2024
|
|
[Question][Unity] MetaSchedule tune_tir output
|
|
5
|
1134
|
August 12, 2024
|
|
Is microTVM still supported?
|
|
4
|
748
|
August 12, 2024
|
|
Relax：is still under development？whether relax only implements some independent pass optimization？
|
|
1
|
548
|
August 9, 2024
|
