@PyTorch: Ujval Kapasi (@nvidia) examines what agentic workloads need from the PyTorch stack in “PyTorch Performance for Agents o…
Summary
Ujval Kapasi of NVIDIA delivers a PyTorchCon 2026 keynote on what agentic workloads demand from the PyTorch stack, using NVIDIA Vera Rubin as a case study for hardware-software co-design across CPUs, GPUs, memory, and networking, covering optimizations in PyTorch, Triton, and vLLM.
View Cached Full Text
Cached at: 10/21/26, 07:22 AM
Ujval Kapasi (@nvidia) examines what agentic workloads need from the PyTorch stack in “PyTorch Performance for Agents on Vera Rubin” at #PyTorchCon 2026.
A single request can trigger long chains of reasoning, tool calls, code execution, data movement, and distributed inference, introducing new bottlenecks and optimization opportunities.
Using Vera Rubin as a case study, he explores hardware and software co-design across CPUs, GPUs, memory, and networking. The keynote covers software optimizations and work across PyTorch, Triton, and vLLM on Vera Rubin.
Similar Articles
@PyTorch: Agentic workloads generate long, expanding context across repeated model calls, tool execution, and parallel subagents.…
PyTorch 博客介绍 NVIDIA Dynamo 如何通过统一的 session 级标识符，将请求级推理服务系统升级为程序感知系统，实现会话感知路由、共享 KV 缓存索引与跨 vLLM/SGLang 的程序化缓存迁移，以高效服务具有长上下文和并行子代理的 agentic 工作负载。
@PyTorch: Enable smarter, longer-thinking agents Scale agentic AI and reinforcement learning by shortening CPU execution time, in…
NVIDIA introduces the Vera CPU with a neural branch predictor to accelerate agentic AI and reinforcement learning workloads by reducing CPU execution time and increasing throughput in AI factories.
@PyTorch: Discover how open source agentic search and hardware-guided workflows are unlocking massive speedups across GPUs and TP…
The PyTorch Conference North America will be held in San Jose, featuring sessions on agentic search, hardware-guided workflows, and AI performance optimization with speakers from major tech companies.
@PyTorch: Keynote Speaker Spotlight Ujval Kapasi, VP of AI & HPC Frameworks & Libraries at @nvidia, is taking the keynote stage a…
Ujval Kapasi, VP of AI & HPC Frameworks & Libraries at Nvidia, is announced as a keynote speaker at PyTorch Conference North America 2026, scheduled for October 20-21 in San Jose, CA.
@PyTorch: Hardware-Aware AI: Building Agentic Systems from Cloud to Edge with PyTorch, ExecuTorch AI agents are moving beyond cha…
The article announces the PyTorch Conference North America 2026, highlighting a session on deploying hardware-aware AI agentic systems on edge devices using PyTorch and ExecuTorch, along with registration information.