OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-06 12:20:52 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity
85,012 Commits 8,304 Branches 150 Tags 1.5 GiB
b7832f0339
Commit Graph

6 Commits

Author SHA1 Message Date
cyy
b7832f0339 Enable ASAN in CUDA tests (#147812) 
Fixes #ISSUE_NUMBER

Pull Request resolved: https://github.com/pytorch/pytorch/pull/147812
Approved by: https://github.com/janeyx99
 2025-03-04 02:50:39 +00:00
Gabriel Ferns
bab35eb26a fix intermediate debug information with cpp_wrapper (#145527) 
Summary: before fix, code like:
```cpp
    aoti_torch_print_tensor_handle(buf0, "after_launch - triton_poi_fused_randn_0 - buf0");
    aoti_torch_print_tensor_handle(buf1, "after_launch - triton_poi_fused_randn_0 - buf1");
    printf("[  after_launch - triton_poi_fused_randn_0 - 0: %ld  ]", 0); printf("
");
    printf("[  after_launch - triton_poi_fused_randn_0 - 1228800L: %ld  ]", 1228800L); printf("
");
```
was generated, which is a syntax error.

Test Plan:
New unit test.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/145527
Approved by: https://github.com/desertfire
 2025-02-10 22:24:26 +00:00
Gabriel Ferns
5a527fa5ee Make sure not using cpp wrapper when setting nvtx training annotation (#145538) 
Longer term would be good to add as a feature to cpp_wrapper, but this makes sure it doesn't fail on main.

Not sure if this needs a test because it's not meant to compose, but will add one if necessary.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/145538
Approved by: https://github.com/desertfire
 2025-01-30 18:34:22 +00:00
xinan.lin
934eaa503f [Inductor XPU] Support max-autotune on XPU and reuse the corresponding Inductor UT. (#143266) 
This PR aims to add the functionality support of max-autotune for XPU. The current triton templates and configurations are not well optimized for XPU, so the performance is not ready yet. Also the `mm_plus_mm` template have accuracy issues in some cases. We will address these issues in the next PRs.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/143266
Approved by: https://github.com/EikanWang, https://github.com/jansel
 2024-12-30 23:51:17 +00:00
Jason Ansel
e343f46464 [inductor] Refactor is_big_gpu (#142220) 
Pull Request resolved: https://github.com/pytorch/pytorch/pull/142220
Approved by: https://github.com/yanboliang
ghstack dependencies: #142219, #142033, #142222
 2024-12-08 18:51:36 +00:00
xinan.lin
b75bb64eb4 [AOTI XPU] Rename test_cuda_cpp_wrapper.py to test_gpu_cpp_wrapper.py, (#135320) 
[Inductor] Rename test_cuda_cpp_wrapper.py to test_gpu_cpp_wrapper.py, since the test suite is shared by cuda and xpu.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/135320
Approved by: https://github.com/jansel, https://github.com/EikanWang, https://github.com/desertfire
ghstack dependencies: #135318
 2024-11-27 14:08:06 +00:00