Metraipolis › archive › dc_e58ccefe37ff

An Empirical Study of Issues in GPU Kernel Libraries for LLM Systems — arXiv:2611.09280

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09280
License (as archived)
CC0-1.0
Archived
2026-11-09T22:34:00.378Z
SHA-256 of the archived text
86e3462249a086360f72d5acbd3b7fe5f312006c175827ed67515e0483bff4c9
Stable URL of this page
https://metraipolis.com/documento/dc_e58ccefe37ff

How to cite

An Empirical Study of Issues in GPU Kernel Libraries for LLM Systems — arXiv:2611.09280 — arXiv (en), https://arxiv.org/abs/2611.09280 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e58ccefe37ff (Metraipolis archive dc_e58ccefe37ff, sha256 86e3462249a086360f72d5acbd3b7fe5f312006c175827ed67515e0483bff4c9)
BibTeX
@misc{dce58ccefe37ff,
  title = {An Empirical Study of Issues in GPU Kernel Libraries for LLM Systems — arXiv:2611.09280},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09280},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e58ccefe37ff; sha256 86e3462249a086360f72d5acbd3b7fe5f312006c175827ed67515e0483bff4c9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09280. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Behind the expanding use of large language models (LLMs) across application domains lies a growing dependence on specialized GPU kernel libraries. These libraries underpin the correctness and efficiency of training and inference across diverse GPU platforms, implementing attention, GEMM, quantization, and low-precision operators while managing tensor shapes, memory layouts, code generation, and hardware-specific dispatch. Problems at this layer can silently corrupt outputs, hang GPUs, prevent compilation, introduce deployment incompatibilities, or degrade performance, thereby reducing developer productivity and wasting expensive GPU resources. We present the first comprehensive empirical study of issues in GPU kernel libraries for LLM systems. We manually analyzed 300 high-quality GitHub issue reports, their discussions, and available fixes from seven representative libraries: FlashInfer, FlashAttention, Triton, CUTLASS, DeepGEMM, xFormers, and bitsandbytes. The analysis characterizes symptoms, root causes, fixes, and testing and debugging practices. Our main findings are: (1) 60.33% of the sampled issues originate in the Compiler and Build System or Runtime Environment dimensions, so validation must cover the deployment and execution stack, not just kernel code. (2) Kernel specialization imposes implicit correctness constraints on tensor shapes, metadata layouts, memory aliasing, and hardware resources. Violations can produce incorrect outputs or launch failures even for supported operations, highlighting the need for explicit contract validation and boundary-case testing. (3) Current testing and debugging practices are often insufficient for identifying low-precision numerical problems and hardware-specific execution failures. We outline research opportunities and tooling directions to support future LLM GPU kernel development.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.09280 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-09T22:30:47.273Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).