PyTorch 2.15 发布：NCCL 新后端成默认，Blackwell 支持 NVFP4 解码
PyTorch 2.15 来了，583 人贡献了 3000 多次提交，Blackwell 上 4-bit 解码更快，Mac 上也支持 FP8 了，训练部署的都看看。
PyTorch 2.15 包含来自 583 位贡献者的 3,117 次提交。重写的 NCCL 后端成为默认，并新增基于 NIXL 的单侧传输。FSDP2 和流水线并行获得更细的显存与通信控制。在 NVIDIA Blackwell GPU 上支持更快的 4-bit（NVFP4）LLM 解码，Apple Silicon 获得 FP8 与更快解码。团队将于 11 月 5 日 11 AM PST 举行线上问答。
PyTorch 2.15 is here, with 3,117 commits from 583 contributors and updates across distributed training, NVGEMM, Apple Silicon, and accelerator platform support.
The release makes the rewritten NCCL backend the default and adds one-sided transports with a NIXL backend. FSDP2 and pipelining gain finer memory and communication control. It also brings faster 4-bit (NVFP4) LLM decoding on NVIDIA Blackwell GPUs, FP8 and faster decode on Apple Silicon, and broader platform support.
On Thursday, November 5, at 11 AM PST, join Tristan Rice (@rice_fry), Natalia Gimelshein, Huy Do, and Jane Xu (@janeyx99) (@Meta) for a live PyTorch 2.15 Q&A, moderated by Chris Gottbrath (Gottbrath Tech). The speakers will share an overview of the release and answer community questions about PyTorch and the new capabilities in this release.
🔗 Read the release blog and register for the live Q&A: https://t.co/PAsbeCXk0C
