|
About the torch._inductor category
|
|
0
|
462
|
December 6, 2022
|
|
In inductor, can we unify the way to generate code between using extern_kernels and torch.ops?
|
|
0
|
1
|
October 3, 2024
|
|
Getting Triton to generate all kernels
|
|
12
|
1511
|
September 7, 2024
|
|
Im following all the steps but i still cant connect my pytorch to gpu
|
|
7
|
269
|
September 4, 2024
|
|
Fusing operators in torch.compile for Codegen
|
|
1
|
58
|
August 12, 2024
|
|
What is ComputedBuffer?
|
|
0
|
104
|
May 24, 2024
|
|
Reverse Fusion of Node Pairs in Scheduler
|
|
0
|
140
|
May 8, 2024
|
|
Generate Triton kernels for CPU
|
|
4
|
460
|
April 26, 2024
|
|
Torch.compile raises error when compiled function calls other functions
|
|
1
|
1874
|
March 22, 2024
|
|
Output runnable backwards _inductor graph `torch.compile`
|
|
0
|
264
|
January 23, 2024
|
|
Prologue fusion
|
|
0
|
429
|
January 23, 2024
|
|
Triton kernel launch in TorchInductor
|
|
1
|
674
|
December 7, 2023
|
|
Torch.compile too slow with SDXL model
|
|
1
|
879
|
December 2, 2023
|
|
Inductor CPP codegen for WebAssembly target
|
|
2
|
528
|
September 27, 2023
|
|
Emit Triton IR/ LLVM IR from TorchInductor
|
|
0
|
460
|
September 21, 2023
|
|
Inductor CPU C++ backend
|
|
0
|
360
|
August 28, 2023
|
|
Correct way to avoid torch.compile recompilations
|
|
1
|
838
|
August 2, 2023
|
|
Torch.compile() error with detach() and with torch.no_grad()
|
|
2
|
705
|
April 20, 2023
|
|
Xblock is not defined
|
|
1
|
693
|
April 19, 2023
|
|
Does torch.compile use FlashAttention？
|
|
5
|
2826
|
April 10, 2023
|
|
Trying to use triton on torch inductor
|
|
1
|
1722
|
March 21, 2023
|
|
BackendCompilerFailed: _compile_fn raised RuntimeError: Triton requires CUDA 11.4+
|
|
23
|
4753
|
February 17, 2023
|
|
Torch 2.0 Dynamo Inductor Does not Work for Huggingface Transformers Text Generation Model
|
|
2
|
2886
|
January 27, 2023
|