diff --git a/_posts/2024-10-15-performance-boost-windows.md b/_posts/2024-10-15-performance-boost-windows.md index 40bf9e63f394..c73859f8b244 100644 --- a/_posts/2024-10-15-performance-boost-windows.md +++ b/_posts/2024-10-15-performance-boost-windows.md @@ -88,7 +88,7 @@ Install PyTorch CPU 2.4.1 or later on Windows from the [official repository](htt ## ACKNOWLEDGMENTS -The results presented in this blog post was achieved through the collaborative effort of the Intel PyTorch team and Meta. We would like to express our sincere gratitude to [Xu Han](https://github.com/xuhancn), [Jiong Gong](https://github.com/jgong5), [Haozhe Zhu](https://github.com/zhuhaozhe), [Mingfei Ma](https://github.com/mingfeima), [Chuanqi Wang](https://github.com/chuanqi129), [Guobing Chen](https://github.com/Guobing-Chen) and [Eikan Wang](https://github.com/EikanWang). Their expertise and dedication have been instrumental in achieving the optimizations and performance improvements discussed here. Thanks to [Jiachen Pu](https://github.com/peterjc123) from community for his participation in the issue discussion and suggesting the use of [mimalloc](https://github.com/microsoft/mimalloc). We’d also like to express our gratitude to Microsoft for providing such an easily integrated and performant mallocation library. Thanks to [Pierre Blanchard](https://github.com/blapie) , [Nathan Sircombe](https://gitlab.com/Nathan.Sircombe) from ARM and [Alex Reinking](https://github.com/alexreinking) from Qualcomm for their contribution in overcome the compatibility issues with the [sleef](https://github.com/shibatch/sleef) integrated to PyTorch Windows. Finally we want to thank [Jing Xu](https://github.com/jingxu10), [Weizhuo Zhang](https://github.com/WeizhuoZhang-intel) and [Zhaoqiong Zheng](https://github.com/ZhaoqiongZ) for their contributions to this blog. +The results presented in this blog post was achieved through the collaborative effort of the Intel PyTorch team and Meta. We would like to express our sincere gratitude to [Xu Han](https://github.com/xuhancn), [Jiong Gong](https://github.com/jgong5), [Haozhe Zhu](https://github.com/zhuhaozhe), [Mingfei Ma](https://github.com/mingfeima), [Chuanqi Wang](https://github.com/chuanqi129), [Guobing Chen](https://github.com/Guobing-Chen) and [Eikan Wang](https://github.com/EikanWang). Their expertise and dedication have been instrumental in achieving the optimizations and performance improvements discussed here. Thanks to [Jiachen Pu](https://github.com/peterjc123) from community for his participation in the issue discussion and suggesting the use of [mimalloc](https://github.com/microsoft/mimalloc). We’d also like to express our gratitude to Microsoft for providing such an easily integrated and performant mallocation library. Thanks to [Pierre Blanchard](https://github.com/blapie) , [Nathan Sircombe](https://github.com/nSircombe) from ARM and [Alex Reinking](https://github.com/alexreinking) from Adobe for their contribution in overcome the compatibility issues with the [sleef](https://github.com/shibatch/sleef) integrated to PyTorch Windows. Finally we want to thank [Jing Xu](https://github.com/jingxu10), [Weizhuo Zhang](https://github.com/WeizhuoZhang-intel) and [Zhaoqiong Zheng](https://github.com/ZhaoqiongZ) for their contributions to this blog. ### Product and Performance Information diff --git a/_videos/vid1.md b/_videos/vid1.md new file mode 100644 index 000000000000..d42b1576182d --- /dev/null +++ b/_videos/vid1.md @@ -0,0 +1,5 @@ +--- +title: 'PyTorch 2.5 Live Q&A' +youtube_id: B3IgXpl4xt4 +date: Oct 21, 2024 +--- diff --git a/_videos/vid2.md b/_videos/vid2.md new file mode 100644 index 000000000000..b7900abc0ec0 --- /dev/null +++ b/_videos/vid2.md @@ -0,0 +1,5 @@ +--- +title: 'DistServe: disaggregating prefill and decoding for goodput-optimized LLM inference' +youtube_id: Bh-jlh5vlF0 +date: Oct 16, 2024 +--- diff --git a/_videos/vid3.md b/_videos/vid3.md new file mode 100644 index 000000000000..92bae2c1fa3e --- /dev/null +++ b/_videos/vid3.md @@ -0,0 +1,5 @@ +--- +title: 'Efficient Streaming Language Models with Attention Sinks' +youtube_id: RnM84Sv9WpA +date: Oct 11, 2024 +--- diff --git a/_videos/vid4.md b/_videos/vid4.md new file mode 100644 index 000000000000..c29ec8d1e005 --- /dev/null +++ b/_videos/vid4.md @@ -0,0 +1,5 @@ +--- +title: 'PyTorch Expert Exchange: Adapting open source models with Open-Instruct and Tulu' +youtube_id: e1qUJFAo10s +date: Sep 11, 2024 +--- diff --git a/_videos/vid5.md b/_videos/vid5.md new file mode 100644 index 000000000000..110c90047648 --- /dev/null +++ b/_videos/vid5.md @@ -0,0 +1,5 @@ +--- +title: 'PyTorch Expert Exchange: Efficient Generative Models: From Sparse to Distributed Inference' +youtube_id: Eqg0VIiWrgM +date: Aug 30, 2024 +--- diff --git a/_videos/vid6.md b/_videos/vid6.md new file mode 100644 index 000000000000..e456938c3d9e --- /dev/null +++ b/_videos/vid6.md @@ -0,0 +1,5 @@ +--- +title: 'torch.compile: The Missing Manual' +youtube_id: rew5CSUaIXg +date: Aug 13, 2024 +--- diff --git a/_videos/vid7.md b/_videos/vid7.md new file mode 100644 index 000000000000..02bea05040a7 --- /dev/null +++ b/_videos/vid7.md @@ -0,0 +1,5 @@ +--- +title: 'Using PyTorch for Monocular Depth Estimation Webinar' +youtube_id: xf2QgioY370 +date: Sep 27, 2024 +--- diff --git a/_videos/vid8.md b/_videos/vid8.md new file mode 100644 index 000000000000..550290a68f3c --- /dev/null +++ b/_videos/vid8.md @@ -0,0 +1,5 @@ +--- +title: 'Accelerating LLM family of models on Arm Neoverse based Graviton AWS processors with KleidiAI' +youtube_id: NeHIhQWewug +date: Aug 22, 2024 +--- diff --git a/_videos/vid9.md b/_videos/vid9.md new file mode 100644 index 000000000000..769901483585 --- /dev/null +++ b/_videos/vid9.md @@ -0,0 +1,5 @@ +--- +title: 'PyTorch 2.4: Live Q&A' +youtube_id: ry_QgUIYX1E +date: Jul 25, 2024 +---