Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation

arXiv:2604.10180 · cs.DC, cs.LG · Submitted 2026-04-11 · Read on arXiv

cs.DC, cs.LG

Submitted: 2026-04-11

Updated: 2026-09-19

Code: https://github.com/pytorch/pytorch

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Analyzer — 20× in this paper · explained in 1 episode
• Decode — 14× in this paper · explained in 2 episodes
• Adaptation — 8× in this paper · explained in 1 episode
• Core — 8× in this paper · explained in 2 episodes
• Diffusion Model — 8× in this paper · explained in 8 episodes
• Communication Overhead — 7× in this paper · explained in 2 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Diffusion Models — 6× in this paper · explained in 6 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Mixed-Integer Linear Programming — 2× in this paper
• Online Adaptation — 2× in this paper · explained in 3 episodes
• Topological Order — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Allocator — 1× in this paper · explained in 1 episode
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Streaming Multiprocessor — 1× in this paper
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding
• HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment
• Open SYCL on heterogeneous GPU systems: A case of study
• FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
• Attention Is All You Need
• Rearchitecting Datacenter Lifecycle for AI: A TCO-Driven Framework
• The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective
• Autellix: An Efficient Serving Engine for LLM Agents as General Programs
• Cronus: Efficient LLM inference on Heterogeneous GPU Clusters via Partially Disaggregated Prefill
• gpt-oss-120b & gpt-oss-20b Model Card
• Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
• Microsoft COCO Captions: Data Collection and Evaluation Server
• Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
• Qwen3 Technical Report
• DeepSeek-V3 Technical Report

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence
• Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
• Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing