What's the current status of tuning support in Dlight?
|
|
1
|
86
|
January 31, 2025
|
Zero pipeline (FuseTIR) has trouble with matching buffers between TIR and Relax operations
|
|
0
|
68
|
January 29, 2025
|
Kernel Launching and Dynamic Kernel Selection for LLMs with Relay
|
|
4
|
719
|
January 26, 2025
|
Will TVM participate in Google Summer of Code?
|
|
1
|
93
|
January 25, 2025
|
Is there a way to use a model with static input but dynamic output?
|
|
4
|
205
|
January 23, 2025
|
What is the recommended way to generate TIR level operations?
|
|
0
|
85
|
January 20, 2025
|
Issue with Tuning Kernels for ResNet-18 on x86 CPU Using TVM
|
|
0
|
85
|
January 18, 2025
|
Deploy Relax IR using C++ API
|
|
2
|
237
|
January 16, 2025
|
Error while transforming Huggingface BERT to TIR
|
|
0
|
126
|
January 13, 2025
|
Is there any way to limit the operations TVMs autoscheduler can use when creating a schedule?
|
|
2
|
136
|
January 10, 2025
|
[Unity] Memory layout rewrite cross-layer feedback optimization
|
|
1
|
166
|
January 7, 2025
|
[auto-tvm]What does a cost model do in auto tuning
|
|
11
|
1826
|
January 5, 2025
|
Execution of microTVM on windows
|
|
1
|
318
|
January 3, 2025
|
How to deploy pytorch model using C++
|
|
1
|
174
|
January 2, 2025
|
Check failed: (calling_conv == CallingConv::kDeviceKernelLaunch) is false: CodeGenOpenCL: expect calling_conv equals CallingConv::kDeviceKernelLaunch
|
|
0
|
80
|
January 1, 2025
|
Model compilation for MIPS targets?
|
|
4
|
630
|
January 1, 2025
|
Target not available while compiling ONNX model to MIPS
|
|
0
|
112
|
January 1, 2025
|
Performance Drop After Compiling Model with TVM Compared to ONNX Runtime
|
|
0
|
136
|
January 1, 2025
|
[translate ONNX to Relax]AttributeError: <class 'tvm.relax.expr.Call'> has no attribute data
|
|
2
|
122
|
December 31, 2024
|
[Release] v0.19.0 Release Schedule
|
|
0
|
145
|
December 27, 2024
|
Unable to compile TVM runtime for MIPS platform
|
|
0
|
117
|
December 26, 2024
|
Proper way to save params with Relax detach_params
|
|
2
|
278
|
December 25, 2024
|
找一些可以一起深入学习 tvm 源码的朋友
|
|
15
|
1927
|
December 22, 2024
|
[build] how to get the tvm execute binary ?
|
|
3
|
224
|
December 20, 2024
|
Large runtime discrepancy between RPC and deploy
|
|
2
|
581
|
December 18, 2024
|
Questions regarding the future development of MicroTVM
|
|
6
|
381
|
December 17, 2024
|
Generating C Code for tvm.relax.op.nn.attention in TVM RELAX
|
|
0
|
146
|
December 16, 2024
|
Some question for running AI models trained in TensorFlow on a Xilinx Ultra96v2 FPGA board
|
|
0
|
132
|
December 16, 2024
|
TorchFX to Relax Op Issue in Web Stable Diffusion
|
|
0
|
123
|
December 16, 2024
|
What does "op": "null", "name": "p0" mean in graph.json
|
|
1
|
260
|
November 7, 2024
|