etaf

[AOTI XPU] Enable Cpp wraper for Intel GPU.

20

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #140686 * #140664 * #140269 * #140819 * #140268 * #135320 * __->__ #135318 cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng...

[AOTI] Fix #140546 and support AOTI package load for Intel GPU.

1

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #140686 * __->__ #140664 * #140269 * #140268 * #135320 * #135318 * #139026 Fix #140546 cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper...

[AOTI XPU] Rename test_cuda_cpp_wrapper.py to test_gpu_cpp_wrapper.py,

2

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #140686 * #140664 * #140269 * #140819 * #140268 * __->__ #135320 * #135318 [Inductor] Rename test_cuda_cpp_wrapper.py to test_gpu_cpp_wrapper.py, since the test suite...

[Intel GPU] Support getStreamFromExternel for XPU.

3

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #140686 * #140664 * #140269 * #140819 * __->__ #140268 * #135320 * #135318 In AOT inductor scenario, the GPU Stream can be...

Reuse test cases in test/export for XPU.

1

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * __->__ #140686 * #140664 * #140269 * #140819 * #140268 * #135320 * #135318 Since we already supported `torch.export` for XPU, this PR...

[AOTI XPU] Support AOT Inductor for Intel GPU.

4

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #140686 * #140664 * __->__ #140269 * #140819 * #140268 * #135320 * #135318 This PR add XPU support for AOT Inductor, and...

[Inductor XPU] Fix wrong device check before skip concat linear.

5

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * __->__ #140916 Fix #140917 cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire...

[AOTI XPU] Add XPUStreamGuard for XPU which is necessary for AOTI.

1

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #140686 * #140664 * #140269 * __->__ #140819 * #140268 * #135320 * #135318 This PR created XPUStreamGuard instead of reuse StreamGuard for...

[Inductor XPU GEMM] Step 9/N: Support generating XPU cutlass gemm kernel

1

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #161940 * __->__ #161939 * #161938 * #160729 * #160706 * #160688 * #160687 * #160686 * #160685 * #160174 This PR implements...

[Inductor XPU GEMM] Step 6/N: Refactor CUDACodeCache.

1

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #161940 * #161939 * #161938 * #160729 * __->__ #160706 * #160688 * #160687 * #160686 * #160685 * #160174 This PR is...