{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T05:10:18Z","timestamp":1756357818866,"version":"3.44.0"},"reference-count":8,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"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":[[2025,7,6]]},"DOI":"10.1109\/isvlsi65124.2025.11130212","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T18:20:15Z","timestamp":1756318815000},"page":"1-2","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Multi-Precision Inference for Large-Scale AI Using IEEE P3109 FP8"],"prefix":"10.1109","author":[{"given":"Arnav","family":"Ramamoorthy","sequence":"first","affiliation":[{"name":"Micron Technology, Inc."}]},{"given":"Kiran Kumar","family":"Gunnam","sequence":"additional","affiliation":[{"name":"Micron Technology, Inc."}]}],"member":"263","reference":[{"journal-title":"Squeezebits Blog","article-title":"Blog Posts on Optimizing Inference","year":"2025","key":"ref1"},{"journal-title":"Character AI Research Blog","article-title":"Optimizing Inference","year":"2025","key":"ref2"},{"key":"ref3","article-title":"Optimizing AI Inference at Character AI: Part Deux","author":"Research","year":"2025","journal-title":"Character AI Research Blog"},{"key":"ref4","article-title":"IEEE P3109 Standard for 8-Bit FloatingPoint Arithmetic (FP8)","author":"Standards Association","year":"2025","journal-title":"IEEE Standard P3109, 2023"},{"journal-title":"NVIDIA Transformer Engine Documentation, 2024","article-title":"Mixed Precision Training with FP8 Primer","year":"2025","key":"ref5"},{"key":"ref6","article-title":"Bits and Business: FP8 Quantization Deepdive","author":"Masood","year":"2024","journal-title":"Medium"},{"journal-title":"OpenVINO Model Optimization Guide","article-title":"Quantizing with Accuracy Control","year":"2025","key":"ref7"},{"journal-title":"OpenVINO Documentation, 2025","article-title":"Inference with Optimum Intel: OpenVINO Runtime Optimizations","year":"2025","key":"ref8"}],"event":{"name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","start":{"date-parts":[[2025,7,6]]},"location":"Kalamata, Greece","end":{"date-parts":[[2025,7,9]]}},"container-title":["2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11129697\/11130193\/11130212.pdf?arnumber=11130212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:31:03Z","timestamp":1756355463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,6]]},"references-count":8,"URL":"https:\/\/doi.org\/10.1109\/isvlsi65124.2025.11130212","relation":{},"subject":[],"published":{"date-parts":[[2025,7,6]]}}}