Tag
PyTorch Con 2026 主题演讲预告:Agentic AI Foundation 执行董事 Mazin Gilbert 探讨 LLM 如何从智能体行为中学习,提出五层智能体栈架构,并将智能体评估反馈为 PyTorch 训练奖励的开放研究方向。
PyTorch Conference North America in San Jose (Oct 20-21) will feature a poster by Bongwoo Bak of Moreh on KV cache block placement, covering vLLM offloading strategies between GPU, CPU, and shared storage. The post also promotes conference registration tiers and pricing.
PyTorch Conference North America (San Jose, Oct 20-21) will feature Carlos Costa of IBM Research and co-founder of llm-d sharing news on how the llm-d project has matured to deliver state-of-the-art performance for generative AI serving, including multi-tenant QoS and zero-downtime operations.
在 PyTorch Conference North America 2026 上,AMD 团队将展示 MoRI 通信栈与 vLLM 结合,实现跨 pod 的宽专家并行(Wide Expert Parallelism)以及基于 RDMA 的 KV 缓存传输,用于 AMD Instinct GPU 上的分离式 MoE 服务。
RadixArk's Yihao Wang and Kevin Mi will present SGLang-Diffusion, a high-performance serving framework for diffusion models, at PyTorch Conference North America 2026 in San Jose (Oct 20-21), covering request scheduling, memory management, batching, and PyTorch-based inference optimizations.
Kaiming Cheng of Meta will present KernelAgent, a hardware-guided multi-agent harness that optimizes GPU Triton kernels, at PyTorch Conference North America 2026; it achieved a 2.02x speedup over prior versions and 1.56x over default torch.compile across 100 KernelBench L1 tasks.
PyTorch Conference North America (Oct 20-21, San Jose) spotlights keynote speaker Zongwei Zhou, Software Engineer at Meta, who will explore how TorchTPU and agent-driven development make complex AI workloads portable and performant across hardware.
PyTorch Conference North America will feature a session by AWS's Esha Lakhotia and Pinak Panigrahi on profiling PyTorch workloads on AWS Trainium, covering torch.profiler capture through cycle-level hardware debugging with AI-assisted analysis. The event takes place in San Jose on October 20-21.
PyTorch Foundation Ambassador Abdulsalam Bande will present a poster on ERRC (Entropy-Reinvested Residual Correction) at PyTorch Conference North America 2026 in San Jose, compressing inter-GPU communication to boost multi-GPU LLM inference efficiency, alongside the broader conference program covering the open-source AI stack.
At PyTorch Conference North America 2026, AMD's Liz Li and Jiahui Cao will present "Extending TorchInductor with FlyDSL," an MLIR-native GPU kernel backend for high-performance GEMMs that integrates with TorchInductor's compilation and autotuning pipeline, with benchmark comparisons against Triton on AMD Instinct GPUs.
PyTorch blog publishes a Ray-focused guide to PyTorch Conference North America 2026 in San Jose, highlighting keynotes and sessions on co-evolving Ray and Kubernetes, elastic training stacks, and scalable RL from speakers at Anyscale, Google, LinkedIn, Pinterest, and Uber.
This post promotes vLLM, a high-throughput inference engine for LLMs, and details its sessions and activities at PyTorchCon North America.
The article promotes a talk at the PyTorch Conference North America focused on making enterprise agentic inference production-ready using PyTorch and vLLM, covering ecosystem updates and registration details.
The article promotes a presentation on Elastic Expert Parallelism in vLLM at the PyTorch Conference North America 2026, discussing how to dynamically add or remove GPUs in Mixture-of-Experts deployments with minimal downtime.
An announcement for a talk at PyTorch Conference North America where Ziming will discuss using OpGuard for bitwise debugging in LLM training.
At PyTorch Conference North America, Maajid Khan from Fujitsu Research India will present a talk on optimizing Mixture of Experts LLM inference on ARM CPUs using vLLM and OpenVINO.
The article promotes a poster presentation at PyTorch Conference North America on enabling the open-source vime RL post-training framework on AMD Instinct GPUs using ROCm, and provides registration details for the conference.
The PyTorch Conference North America 2026 will feature a session by Red Hat engineers on Cross-Repository CI Relay to streamline CI integration for downstream repositories. Registration details and event highlights are provided.
At PyTorch Conference North America 2026, Dhritiman Das will present a torch-native retrieval engine that uses PyTorch as the primary runtime for retrieval, filtering, and ranking, designed for scalable use cases like feed and search at LinkedIn.
The PyTorch Conference North America in 2026 will feature a talk by Chris Lattner on a unified software stack to address fragmentation in the AI ecosystem, with registration details provided.