If you have ever wanted to actually build an LLM inference runtime yourself — pack your own weights, own every barrier, capture your own CUDA graphs — this is what that journey looks like on an H100. A step-by-step tour of a small runtime called annotated-llm-runtime, and the three bugs that produced most of the annotations.
arXiv:2511. 10480v3 Announce Type: replace-cross Abstract: Optimizing the performance of large language models (LLMs) on large-scale AI training and inference systems requires a scalable and expressive mechanism to model distributed workload execution.
arXiv:2606. 04023v1 Announce Type: cross Abstract: While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated environments (e.
arXiv:2606. 07665v1 Announce Type: cross Abstract: Transformer inference increasingly depends on specialized compiler and runtime support, but real model graphs still require semantic decisions about which regions are worth specializing and which CUDA implementation families are plausible.
arXiv:2607. 16669v1 Announce Type: cross Abstract: OpenLanguageModel (OLM) is an open-source PyTorch library for building and pretraining small language models while keeping their machinery visible.
arXiv:2604. 01489v2 Announce Type: replace Abstract: High-performance GPU kernels are critical to modern machine learning systems, yet developing them remains a manual, expert-driven process.
arXiv:2512. 22219v2 Announce Type: replace-cross Abstract: We introduce Mirage Persistent Kernel (MPK), the first compiler and runtime system that automatically transforms multi-GPU model inference into a single high-performance mega-kernel.
arXiv:2607. 02521v1 Announce Type: cross Abstract: SwiGLU is the dominant MLP activation in modern large language models, yet its intermediate tensor materialization costs 9-37% of MLP execution time.
arXiv:2607. 28848v1 Announce Type: cross Abstract: LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak.
arXiv:2601. 15727v3 Announce Type: replace Abstract: The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorithmic semantics into low-level hardware operations.
arXiv:2605. 29128v2 Announce Type: replace Abstract: The wide adoption of LLMs has led to their use in great variety of applications and scenarios, such as chatbot assistants and data annotation, creating the need for the models to satisfy certain budget and hardware constraints.
arXiv:2608. 15975v1 Announce Type: cross Abstract: Labeling large text corpora with LLM teachers has become a practical route to training data at scale.
Beat the 8GB VRAM limit. Learn how to run three different LLMs on a single 8GB GPU using C++ layer multiplexing and admission control.