From 57ab39f7e46b0ca8fe8eda73eb8c50fa874eb4df Mon Sep 17 00:00:00 2001 From: "Cui, Yifeng" Date: Tue, 5 Aug 2025 01:46:11 +0000 Subject: [PATCH] Update torch-xpu-ops commit pin (#159621) Update the torch-xpu-ops commit to [intel/torch-xpu-ops@1f7a57](https://github.com/intel/torch-xpu-ops/commit/1f7a57f50745a429b7da10dddf2e366687659b87) includes: - Add Template Parameter to the function `gpu_kernel` for Controlling Broadcasting Vectorization - Add optional NaN checks to XCCL - Fix NllLossForwardReduce2DKernelFunctor accuracy - Extend the existing communication logging to include the reduction operation for collective calls - [Reland] Install xpu codegen header to torch/include Pull Request resolved: https://github.com/pytorch/pytorch/pull/159621 Approved by: https://github.com/EikanWang --- third_party/xpu.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/third_party/xpu.txt b/third_party/xpu.txt index f3cfe7166aa7..b84ebb55a901 100644 --- a/third_party/xpu.txt +++ b/third_party/xpu.txt @@ -1 +1 @@ -3a9419c8bb6a98dd3e3cd473c36691fb4abeae40 +1f7a57f50745a429b7da10dddf2e366687659b87