How do you keep @vllm_project moving at the speed of light without excluding users who run diverse models on diverse hardware? In a new PyTorch Foundation blog, contributors from @IBM, @Meta, and @huggingface introduce hardware-agnostic layers designed to balance frontier performance with portability, helping ensure vLLM continues to meet the needs of the broader open source ecosystem. Read the blog to learn more: @hmellor_ @th_ortner

New chips are shipping faster than ever before, but the ecosystem is being held back by having to rewrite and then re-debug the same code over & over again. @clattner_llvm CEO and Co-founder at @Modular and EVP of Advanced AI Software & Platforms at @Qualcomm, will deliver a keynote at PyTorch Conference North America about an open software platform for heterogeneous compute powered by Mojo and MAX. PyTorch has always been the place where the best models come together, and now there's a way to get those models onto all kinds of hardware. If you're interested in Al and compute, join us at the PyTorch Conference in San Jose, CA. Register now: #PyTorchCon#

🏋️ Train smarter. From distributed training to optimization techniques and foundation models, the Training Track at #PyTorchCon# North America, Oct 20-21 in San Jose, is packed with practical sessions to help you build faster, more efficient AI systems. Learn more: 📅 Schedule: 🎟️ Register:

At PyTorch Conference North America 2026, Nicolò Lucchesi, Research Engineer at @MistralAI and vLLM maintainer, will present joint work with @AWS and @RedHat on how disaggregated serving in vLLM has evolved to support the latest generation of hybrid models. This session will cover the evolution of disaggregated serving for modern hybrid architectures, protocol developments aimed at reducing end-to-end latency, and new key-value pinning mechanisms designed for reliability at scale. Join us in San Jose on October 20-21: #PyTorchCon# @vllm_project

The PyTorch Korea User Group will host its inaugural offline conference on Saturday, November 21, 2026, hosted at AWS Korea in Centerfield East, Seoul. Designed around the end-to-end AI lifecycle, the event features three primary tracks: Build, Serve, and Run. Community members, developers, and researchers are invited to submit session proposals highlighting real-world project wins, takeaways from failed experiments, or core performance optimizations. The deadline to submit proposals is Sunday, September 13, 2026, at 23:59 KST. Submit your talk today:

PyTorch Day Japan 2026 comes to Tokyo on December 10, and the call for proposals is officially OPEN! We're accepting proposals for session presentations and Lightning Talks across the full spectrum of open source AI, PyTorch, and AI/ML. Suggested topics include: 🚀 Sovereign AI (Local & Open Models) 🏋️ Physical AI & Edge AI 💡 PyTorch Ecosystem Submit a Proposal by September 27 at 11:59 pm JST >>

Join Thomas Cottenier from @Arm at PyTorch Conference North America in San Jose this October 20-21. Thomas will present how AI agents can synthesize customized, target-specific runtimes using PyTorch components like torch.export, ExecuTorch, and torchao. This approach removes redundant prefill computation and creates streamlined inference pipelines that deliver high performance directly on edge hardware. Register now for PyTorch Conference North America: #PyTorchCon#

Learn how to optimize financial portfolio grouping through a PyTorch-enabled, GPU-accelerated clustering pipeline which delivers hard labels, soft factor loadings, and structural-break signals at scale. Built to rerun cost-effectively as new returns arrive, it seamlessly transitions from a single GPU to multi-node setups without changing the solver interface. Explore the complete technical breakdown and reproducible companion notebook on the @nvidia Technical Blog:

🎤 Meet keynote speaker Zhipeng Wang (@PKUWZP), Senior Staff Software Engineer at @Google and DeepSpeed maintainer. At #PyTorchCon# North America, he’ll share advances helping DeepSpeed train large models efficiently across diverse hardware. October 20-21 | San Jose Register:

KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026 brought the people working across the open source AI stack together in Shanghai. @sparkycollier No single project, company, or community builds the AI stack alone. Behind the models, frameworks, cloud native technologies, and infrastructure powering AI is a global open source community working across every layer. PyTorch Foundation welcomed @alibaba_cloud and Cambricon (寒武纪) as Platinum Members and @AntGroup as a Gold Member, joining @Huawei and other existing Foundation members. Across the program, maintainers, researchers, developers, hardware vendors, and technical leaders discussed PyTorch, distributed training, inference and serving, heterogeneous hardware, cloud native infrastructure, accelerator integration, and agents, with participation from the @CloudNativeFdn and @openinfradev communities. Our recap covers keynotes from across the open source AI stack, China-based PyTorch contributors and organizations, the PyTorch TAC Accelerator Integration Working Group, the Foundation press conference, and community conversations in Shanghai. PyTorch conferences are the open source AI community’s town square, where what’s next gets decided. If you couldn’t join us in Shanghai, PyTorch Conference North America 2026 is the next chance to hear directly from maintainers, researchers, developers, and AI engineers working across the open source AI stack. PyTorch Conference North America comes to San Jose October 20–21, with maintainers from PyTorch, @vllm_project, @DeepSpeedAI, and @raydistributed among the speakers. 🔗 Read the Shanghai recap and register for PyTorch Conference North America 2026: #PyTorchCon# #KubeCon# #CloudNativeCon# #OpenInfraSummit#

A conference for people doing the work. 💪 #PyTorchCon# North America, Oct 20-21 in San Jose, brings together a hands-on community of developers, researchers, engineers, maintainers, and practitioners building with #AI# and ML. Come meet the people building what’s next.

At PyTorch Conference North America, Ricardo Noriega de Soto, Tech Lead for the vLLM Omni team and Alexander Brooks, Principal Machine Learning Engineer @RedHat, will demonstrate how extending vLLM’s prefix caching mechanism to multistage pipelines boosts inference speeds while reducing GPU memory overhead. Join us in San Jose on October 20th to learn practical strategies for optimizing complex AI workloads: #PyTorchCon# @vllm_project

🎤 Meet keynote speaker Jana van Greunen, Director of PyTorch Engineering at @Meta. At #PyTorchCon# North America, Jana will share how Meta’s AI workloads are advancing #PyTorch# across hardware, research, and production. 📅 October 20-21 | San Jose Register:

That’s a wrap on Day 2 keynotes! Visit the team at the PyTorch Foundation booth (G2) in the Solutions Showcase to talk about the work happening across the open source AI stack, from frameworks, compilers, and inference to hardware, infrastructure, and agents. Walk through the Project Pavilion while you’re here. Stop by the @DeepSpeedAI table now until 12:45 pm, then find Safetensors from 1:15 to 3:30 p.m. 🔗 #PyTorchCon# #KubeCon# #CloudNativeCon# #OpenInfraSummit#

No single project, company, or community builds the AI stack alone. Behind the models, frameworks, cloud native technologies, & infrastructure powering AI is a global open source community working across every layer. Jane Lyu of @linuxfoundation, Fupan Li of @AntGroup, @Zesheng_Zong of @Huawei, Sunny Chan of TCC demonstrate how collaboration between projects & communities turns individual technologies into an open, interoperable AI ecosystem at #KubeCon# #OpenInfraSummit# #PyTorchCon# China 2026 @CloudNativeFdn @openinfradev @PyTorch

As model complexity and multi-agent workloads continue to grow, Trong Vinh Nguyen explains how Viettel unified a messy reality into a single platform by layering three open source ecosystems: @openinfradev at the bare-metal layer, @CloudNativeFdn tooling for GPU pooling and multi-tenant slicing, and @PyTorch Foundation projects for serving optimization. The result is a Token-as-a-Service platform that treats every GPU in the fleet (old or new) as a productive contributor.

More than 250 organizations across China contribute to PyTorch Foundation projects, including @DeepSpeedAI, Helion, PyTorch, @raydistributed, Safetensors, and @vllm_project. “Open source has become the default way the world builds AI, and the PyTorch Foundation is a leading hub for this innovation,” said @sparkycollier, Executive Director of the PyTorch Foundation. “Welcoming @alibaba_cloud, Cambricon, and @AntGroup as members alongside @Huawei further strengthens the global open source AI ecosystem and community building the open source intelligence layer developers rely on for training, optimizing, serving, distributing, and running models. PyTorch Conference China brings that community together in Shanghai to continue learning from one another.” Alibaba Cloud and Cambricon have joined the PyTorch Foundation as Platinum members, and Ant Group has joined as a Gold member. Representatives from the three new member companies and Huawei are delivering keynotes at PyTorch Conference China on advancing the open AI stack, covering hardware, models, and infrastructure throughout the conference. Alibaba Cloud’s Qwen infrastructure team is walking through how they serve Qwen at massive scale. Huawei will explore hardware-software co-design and the interoperability needed between Chinese and global AI technology stacks. Cambricon is detailing how the company is hardening PyTorch’s device-agnostic foundation so any backend can offer broader reach and richer native capabilities. Ant Group is showing how existing cloud native building blocks can be assembled into a secure, on-demand runtime for AI agents. Taken together, these keynotes move from silicon to software to deployment, giving conference attendees a full-stack view of how open source is being built into every layer of AI in China. 🔗 Read the press release:

vLLM (@vllm_project) sessions at #PyTorchCon# NA 2026 show how teams are optimizing inference, working on PyTorch release validation and compatibility, and using vLLM in broader serving and application workflows. Speakers will cover CUTLASS, Triton, and Helion; faster model loading with fastsafetensors; quantization and HiFloat; autonomous kernel bring-up and Intel GPU optimization; PyTorch release validation, enterprise agentic inference, stable ABI, and dynamic shapes; vision-language serving; cloud-to-edge workflows; high-speed storage; a serving stack for a physics-constrained generative model; and contributor onboarding and first-PR workflows. Featured speakers include: @nvidia: Michael Goldfarb, Guray Ozen, Aastha Jhunjhunwala, and @MarkMoyou @Meta: Andrey Talman, @janeyx99, and Laith Sakka @Arm: Kavya Sri Chennoju @IBM: Takeshi Yoshimura and Nili Guy @RedHat: Markell Rawls, Joseph Groenenboom, Tyler Michael Smith, Sean McGovern, Christopher Leonard, and Maroon Ayoub @Google: Ankita Luthra and Trinadh Kotturu @intel: Xiaogang Gu, Qun Yang, Whitney Tsang, and Artur Fierka @Huawei: Yun Zhao and Haonan Zhang @IBMResearch: Burkhard Ringlein @UMNews: @arunshar08 Register by September 4 to save: Read the vLLM session guide:

vLLM @vllm_project sessions at #PyTorchCon# NA 2026 span the serving stack, from attention and KV cache management to disaggregated serving and hardware portability across accelerators. Speakers will cover attention and KV cache systems, disaggregated serving, expert parallelism, and vLLM across TPU, Trainium, Arm, and IBM Spyre. Featured speakers include: @RedHat: Lucas Wilkinson, Matthew Bonanni, Zhanqiu Hu, @rickynds, and Alex Brooks @amazon: Sunita Nadampalli @IBM: Or Ozeri, Thomas Parnell, and Dave Grove @Huawei: Mengqing Cao @nvidia: Itay Alroy @Google: @Rob_Mulla and Qi Zhou @awscloud: Maen Suleiman @Meta: Richard Zou, Colin Taylor, and Angela Yi @BAAIBeijing: Yonghua Lin @fujitsulabs: Abhishek Jain and N Maajid Khan @IBMResearch: Antoni Viros i Martin and Avery Blanchard @MistralAI: Nicolò Lucchesi @tensormesh: @this_will_echo @googlecloud: Bill Jia Register by September 4 to save: Read the vLLM session guide: