{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T06:08:11Z","timestamp":1792130891187,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","funder":[{"name":"U.S. DOE Office of Science-Advanced Scientific Computing Research Program","award":["DE-AC02-06CH1135"],"award-info":[{"award-number":["DE-AC02-06CH1135"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767346","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:13:44Z","timestamp":1762532024000},"page":"52-60","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5240-5064","authenticated-orcid":false,"given":"Aditya","family":"Tanikanti","sequence":"first","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9986-8816","authenticated-orcid":false,"given":"Benoit","family":"C\u00f4t\u00e9","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3731-5423","authenticated-orcid":false,"given":"Yanfei","family":"Guo","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7188-6756","authenticated-orcid":false,"given":"Le","family":"Chen","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1484-8585","authenticated-orcid":false,"given":"Nickolaus","family":"Saint","sequence":"additional","affiliation":[{"name":"The University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6781-7432","authenticated-orcid":false,"given":"Ryan","family":"Chard","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4705-2713","authenticated-orcid":false,"given":"Ken","family":"Raffenetti","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5532-3048","authenticated-orcid":false,"given":"Rajeev","family":"Thakur","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5631-0142","authenticated-orcid":false,"given":"Thomas","family":"Uram","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2129-5269","authenticated-orcid":false,"given":"Ian","family":"Foster","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6418-5767","authenticated-orcid":false,"given":"Michael E.","family":"Papka","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA and University of Illinois Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7248-6116","authenticated-orcid":false,"given":"Venkatram","family":"Vishwanath","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"ALCF Sophia","unstructured":"[n. d.]. ALCF Sophia. https:\/\/www.alcf.anl.gov\/sophia"},{"key":"e_1_3_3_2_3_2","unstructured":"2025. The Gardens.ai Platform. https:\/\/thegardens.ai\/. Accessed: 2025-01-10."},{"key":"e_1_3_3_2_4_2","unstructured":"Altair. [n. d.]. PBS Professional Scheduler. https:\/\/altair.com\/pbs-professional\/"},{"key":"e_1_3_3_2_5_2","unstructured":"Amazon Web Services. 2024. AWS Batch for Machine Learning. https:\/\/aws.amazon.com\/batch\/."},{"key":"e_1_3_3_2_6_2","unstructured":"Argonne National Laboratory. [n. d.]. AuroraGPT. https:\/\/auroragpt.anl.gov\/. Accessed: April 10 2025."},{"key":"e_1_3_3_2_7_2","unstructured":"Artillery Project. 2025. Artillery - Modern load testing and smoke testing for SRE and DevOps. https:\/\/www.artillery.io. Accessed: 2025-04-14."},{"key":"e_1_3_3_2_8_2","unstructured":"Russell Bryant et\u00a0al. 2025. [RFC]: Scale the API server across multiple CPUs #12705. https:\/\/github.com\/vllm-project\/vllm\/issues\/12705. GitHub Issue."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392683"},{"key":"e_1_3_3_2_10_2","unstructured":"Beno\u00eet Chesneau Paul\u00a0J. Davis et\u00a0al. [n. d.]. Gunicorn: Python WSGI HTTP Server for UNIX. https:\/\/gunicorn.org."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00178"},{"key":"e_1_3_3_2_12_2","unstructured":"Tom Christie et\u00a0al. [n. d.]. Uvicorn: ASGI web server implementation for Python. https:\/\/www.uvicorn.org\/."},{"key":"e_1_3_3_2_13_2","unstructured":"Tom Christie and contributors. 2025. Django REST framework. https:\/\/www.django-rest-framework.org\/. Version 3.14.0."},{"key":"e_1_3_3_2_14_2","unstructured":"ShareGPT Contributors. 2023. ShareGPT: Crowdsourced Conversations for Instruction Tuning. https:\/\/huggingface.co\/datasets\/anon8231489123\/ShareGPT_Vicuna_unfiltered. Accessed: 2025-04-11."},{"key":"e_1_3_3_2_15_2","unstructured":"Joshua M.\u00a0L. Davis. 2021. Django Ninja. https:\/\/django-ninja.dev\/"},{"key":"e_1_3_3_2_16_2","unstructured":"Tim Dettmers et\u00a0al. 2022. LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.07339 (2022)."},{"key":"e_1_3_3_2_17_2","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2025. The Faiss library. arxiv:https:\/\/arXiv.org\/abs\/2401.08281\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.08281"},{"key":"e_1_3_3_2_18_2","unstructured":"Argonne Leadership\u00a0Computing Facility. [n. d.]. Sophia Documentation. https:\/\/www.alcf.anl.gov\/sophia"},{"key":"e_1_3_3_2_19_2","unstructured":"Argonne Leadership\u00a0Computing Facility. 2024. Polaris System Documentation. https:\/\/www.alcf.anl.gov\/polaris"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.11630143"},{"key":"e_1_3_3_2_21_2","unstructured":"Center for AI-Innovation. [n. d.]. llm-serving. https:\/\/github.com\/Center-for-AI-Innovation\/llm-serving"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Ian Foster. 2011. Globus Online: Accelerating and Democratizing Science through Cloud-Based Services. IEEE Internet Computing 15 3 (2011) 70\u201373. 10.1109\/MIC.2011.64","DOI":"10.1109\/MIC.2011.64"},{"key":"e_1_3_3_2_23_2","unstructured":"Google Cloud. 2024. Cloud TPU. https:\/\/cloud.google.com\/tpu."},{"key":"e_1_3_3_2_24_2","unstructured":"Hugging Face. 2024. Text Generation Inference. https:\/\/github.com\/huggingface\/text-generation-inference."},{"key":"e_1_3_3_2_25_2","unstructured":"IBM. [n. d.]. LSF Scheduler. https:\/\/www.ibm.com\/docs\/en\/spectrum-lsf\/10.1.0\/"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43943-8_1"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_3_2_28_2","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 793, 16\u00a0pages."},{"key":"e_1_3_3_2_29_2","unstructured":"Microsoft. 2024. Azure HPC + AI. https:\/\/azure.microsoft.com\/en-us\/solutions\/high-performance-computing\/."},{"key":"e_1_3_3_2_30_2","unstructured":"Inc. NGINX. 2004. NGINX: High Performance Web Server and Reverse Proxy. https:\/\/nginx.org. Accessed April 10 2025."},{"key":"e_1_3_3_2_31_2","unstructured":"NVIDIA. 2024. TensorRT-LLM. https:\/\/github.com\/NVIDIA\/TensorRT-LLM."},{"key":"e_1_3_3_2_32_2","unstructured":"Open WebUI. 2025. Open WebUI. https:\/\/openwebui.com\/. Accessed: 2025-08-11."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Michael\u00a0H. Prince Henry Chan Aikaterini Vriza Tao Zhou Varuni\u00a0K. Sastry Yanqi Luo Matthew\u00a0T. Dearing Ross\u00a0J. Harder Rama\u00a0K. Vasudevan and Mathew\u00a0J. Cherukara. 2024. Opportunities for retrieval and tool augmented large language models in scientific facilities. npj Computational Materials 10 1 (2024) 251. 10.1038\/s41524-024-01423-2","DOI":"10.1038\/s41524-024-01423-2"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Sriram Sagi. 2025. Optimizing LLM Inference: Metrics that Matter for Real Time Applications. Journal of Artificial Intelligence & Cloud Computing 4 1 (2025) 1\u20134. 10.47363\/JAICC\/2025(4)446","DOI":"10.47363\/JAICC\/2025(4)446"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2016.7870901"},{"key":"e_1_3_3_2_36_2","unstructured":"vLLM Project Contributors. 2025. vLLM Benchmark Serving Script. https:\/\/github.com\/vllm-project\/vllm\/blob\/main\/benchmarks\/benchmark_serving.py. Accessed: April 10 2025."},{"key":"e_1_3_3_2_37_2","unstructured":"Moritz Wallawitsch. 2024. Introduction to vLLM and PagedAttention. https:\/\/blog.runpod.io\/introduction-to-vllm-and-how-to-run-vllm-on-runpod-serverless\/. RunPod Blog."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607067"},{"key":"e_1_3_3_2_39_2","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang Tri\u00a0Dao","year":"2023","unstructured":"Tri\u00a0Dao Zhang et\u00a0al. 2023. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_2_40_2","unstructured":"Lianmin Zheng Liangsheng Yin Zhiqiang Xie Chuyue Sun Jeff Huang Cody\u00a0Hao Yu Shiyi Cao Christos Kozyrakis Ion Stoica Joseph\u00a0E. Gonzalez Clark Barrett and Ying Sheng. 2024. SGLang: Efficient Execution of Structured Language Model Programs. arxiv:https:\/\/arXiv.org\/abs\/2312.07104\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2312.07104"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T07:33:16Z","timestamp":1786519996000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767346"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":39,"alternative-id":["10.1145\/3731599.3767346","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767346","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}