PyTorch Conference North America 2026
An annual technical conference organized by the PyTorch Foundation in North America, focused on the PyTorch ecosystem and AI systems research. It includes poster sessions and speaking sessions.
Core Facts
Timeline (last 90 days)
Huan Ran will present this work in the poster session at PyTorch Conference North America 2026 (October 20, Community area).
AMD engineer Huan Ran presented a scheme called FlexBudget in a poster session at PyTorch Conference North America 2026, aiming to solve the methodological problem of rules and implementations being entangled when comparing KV cache eviction strategies.
The three core themes of PyTorch Conference North America 2026 are open research, toolchain, and performance optimization.
The PyTorch Conference 2026 agenda covers dimensions including agent training, agent serving in production environments, agents capable of building PyTorch itself, and applications of PyTorch in the physical world.
vLLM spans multiple technical topics in the PyTorch Conference North America 2026 agenda, including KV cache management, disaggregated serving, hardware portability, kernel optimization, MoE inference, attention mechanisms, and production deployment.
PyTorch Conference North America 2026 will be held on October 20–21 in San Jose, USA.
PyTorch Conference 2026 organized its hardware acceleration and computing infrastructure topics around three keywords: fast, portable, and reliable.
All Facts (7)
PyTorch Conference North America 2026 will be held on October 20–21 in San Jose, USA.
75%UnverifiedThe three core themes of PyTorch Conference North America 2026 are open research, toolchain, and performance optimization.
50%UnverifiedHuan Ran will present this work in the poster session at PyTorch Conference North America 2026 (October 20, Community area).
50%UnverifiedAMD engineer Huan Ran presented a scheme called FlexBudget in a poster session at PyTorch Conference North America 2026, aiming to solve the methodological problem of rules and implementations being entangled when comparing KV cache eviction strategies.
50%UnverifiedThe PyTorch Conference 2026 agenda covers dimensions including agent training, agent serving in production environments, agents capable of building PyTorch itself, and applications of PyTorch in the physical world.
50%UnverifiedvLLM spans multiple technical topics in the PyTorch Conference North America 2026 agenda, including KV cache management, disaggregated serving, hardware portability, kernel optimization, MoE inference, attention mechanisms, and production deployment.
50%UnverifiedPyTorch Conference 2026 organized its hardware acceleration and computing infrastructure topics around three keywords: fast, portable, and reliable.
50%