{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T04:40:05Z","timestamp":1768970405383,"version":"3.49.0"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,18]]},"DOI":"10.1109\/hipc62374.2024.00018","type":"proceedings-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:05:39Z","timestamp":1740081939000},"page":"89-99","source":"Crossref","is-referenced-by-count":4,"title":["CAR-LLM: Cloud Accelerator Recommender for Large Language Models"],"prefix":"10.1109","author":[{"given":"Ashwin","family":"Krishnan","sequence":"first","affiliation":[{"name":"TCS Research,Mumbai,India"}]},{"given":"Venkatesh","family":"Pasumarti","sequence":"additional","affiliation":[{"name":"TCS Research,Mumbai,India"}]},{"given":"Samarth","family":"Inamdar","sequence":"additional","affiliation":[{"name":"TCS Research,Mumbai,India"}]},{"given":"Arghyajoy","family":"Mondal","sequence":"additional","affiliation":[{"name":"TCS Research,Mumbai,India"}]},{"given":"Manoj","family":"Nambiar","sequence":"additional","affiliation":[{"name":"TCS Research,Mumbai,India"}]},{"given":"Rekha","family":"Singhal","sequence":"additional","affiliation":[{"name":"TCS Research,Mumbai,India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86523-8_41"},{"key":"ref3","author":"Naveed","year":"2024","journal-title":"A comprehensive overview of large language models"},{"key":"ref4","article-title":"Chatgpt-4","volume-title":"OpenAI","year":"2024"},{"key":"ref5","author":"Jones","year":"2024","journal-title":"People cannot distinguish gpt-4 from a human in a turing test"},{"key":"ref6","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","author":"Minaee","year":"2024","journal-title":"Large language models: A survey"},{"key":"ref8","author":"Zhao","year":"2023","journal-title":"A survey of large language models"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"ref10","volume-title":"EleutherAI","year":"2023"},{"key":"ref11","volume-title":"The history of open-source LLMs: Early days","author":"WOLFE","year":"2023"},{"key":"ref12","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.13088\/jiis.2024.30.1.093"},{"key":"ref14","author":"Christophe","year":"2024","journal-title":"Med42 - evaluating fine-tuning strategies for medical LLMs: Full-parameter vs. parameter-efficient approaches"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.54364\/AAIML.2023.1191"},{"key":"ref16","volume-title":"Habana Gaudi-2 AI Training Processor","author":"Labs"},{"key":"ref17","article-title":"AWS Inferentia","volume-title":"Amazon Web Services"},{"key":"ref18","article-title":"NVIDIA V100 Tensor Core GPU","volume-title":"NVIDIA"},{"key":"ref19","article-title":"NVIDIA A100 Tensor Core GPU","volume-title":"NVIDIA"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"},{"key":"ref21","article-title":"Cloud TPUs","volume-title":"Google Cloud"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286149"},{"key":"ref23","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"USENIX Symposium on Operating Systems Design and Implementation","author":"Yu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref25","article-title":"Tensorrt-LLM: High-performance inference of large language models with tensorrt","volume-title":"NVIDIA","year":"2024"},{"key":"ref26","article-title":"Mlperf inference: Data center","volume-title":"MLCommons","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624257"},{"key":"ref28","volume-title":"Habana gaudi-2 and mixed-precision training on transformers with bloom","author":"Face","year":"2023"},{"key":"ref29","volume-title":"Llama performance on aws inferentia2 (latency & througput)","author":"Face","year":"2023"},{"key":"ref30","article-title":"Amazon EC2 Inf2 Instances for Low-Cost, High-Performance Generative AI Inference are Now Generally Available","volume-title":"AWS News Blog"},{"key":"ref31","article-title":"High-Performance Llama 2 Training and Inference with PyTorch\/XLA on Cloud TPUs","volume-title":"PyTorch\/XLA Team"},{"key":"ref32","author":"Agrawal","year":"2024","journal-title":"Vidur: A large-scale simulation framework for LLM inference"},{"key":"ref33","volume-title":"Aws trusted advisor","author":"Services","year":"2024"},{"key":"ref34","article-title":"Azure monitor","volume-title":"Microsoft","year":"2024"},{"key":"ref35","volume-title":"Cloud Optimization Best Practices for AWS, Azure, and GCP","author":"Shmuely"},{"key":"ref36","volume-title":"The benefits and limitations of Google Cloud Recommender","author":"Tozzi"},{"key":"ref37","volume-title":"Skypilot","author":"Team","year":"2024"},{"key":"ref38","volume-title":"LLM and ai advancements ignite a new chapter of finops","author":"Everett","year":"2023"},{"key":"ref39","volume-title":"How to forecast ai services costs in cloud","author":"Foundation","year":"2024"},{"key":"ref40","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref41","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","article-title":"Mixtral of experts","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"265","article-title":"{TensorFlow}: a system for {Large-Scale} machine learning","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi","year":"2016"},{"key":"ref44","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref45","author":"Bradbury","year":"2018","journal-title":"JAX: composable transformations of Python+NumPy programs"},{"key":"ref46","article-title":"Aws neuron documentation","volume-title":"AWS","year":"2024"},{"key":"ref47","article-title":"Xla: Compiling machine learning for peak performance","author":"Sabne","year":"2020","journal-title":"Google Res"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC58850.2023.00026"},{"key":"ref49","article-title":"Cuda, release: 10.2.89","author":"Vingelmann","year":"2020","journal-title":"NVIDIA"},{"key":"ref50","author":"Kurtic","year":"2023","journal-title":"Ziplm: Inference-aware structured pruning of language models"},{"key":"ref51","article-title":"Aws cost explorer pricing","volume-title":"I. Amazon Web Services","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref53","article-title":"Powell\u2019s method - Wikipedia, the free encyclopedia","volume-title":"Wikipedia contributors","year":"2023"},{"key":"ref54","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","author":"Lu","year":"2024","journal-title":"The ai scientist: Towards fully automated open-ended scientific discovery"}],"event":{"name":"2024 IEEE 31st International Conference on High Performance Computing, Data, and Analytics (HiPC)","location":"Bangalore, India","start":{"date-parts":[[2024,12,18]]},"end":{"date-parts":[[2024,12,21]]}},"container-title":["2024 IEEE 31st International Conference on High Performance Computing, Data, and Analytics (HiPC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10883940\/10884090\/10884499.pdf?arnumber=10884499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:01:28Z","timestamp":1740121288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10884499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/hipc62374.2024.00018","relation":{},"subject":[],"published":{"date-parts":[[2024,12,18]]}}}