Purlin: Separating Orchestration from the Datapath of Collectives
cs.DC, cs.AI
Submitted: 2026-09-29
Updated: 2026-10-13
Code: https://github.com/purlin-project/purlin
Project page: https://nvidia.github.io/cccl/unstable/cub/index.html
Sources
- CuTe Layout Representation and Algebra
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
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
- Democratizing MoE inference on commodity GPUs with CoMoE