KOSMOS: Self-scheduling Persistent Kernels for Communication-Compute Overlap
cs.DC, cs.AI, cs.LG, cs.PF
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/ROCm/rocm-systems
Terminology
Sources
- Iris: First-Class Multi-GPU Programming Experience in Triton
- FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion
- DeepSeek-V3 Technical Report
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- The Llama 3 Herd of Models
- Recipes for Pre-training LLMs with MXFP8
- Microscaling Data Formats for Deep Learning
- Mixture-of-Kittens: MoE Megakernel for NVL72s
- Qwen3 Technical Report
- Triton-distributed: Programming Overlapping Kernels on Distributed AI Systems with the Triton Compiler
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends