{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T21:43:31Z","timestamp":1773265411842,"version":"3.50.1"},"reference-count":7,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,19]]},"DOI":"10.1109\/asp-dac66049.2026.11420766","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:51:15Z","timestamp":1773172275000},"page":"233-236","source":"Crossref","is-referenced-by-count":0,"title":["TFLOP: Towards Energy-Efficient LLM Inference An FPGA-Affinity Accelerator with Unified LUT-based OPtimization"],"prefix":"10.1109","author":[{"given":"Zongwu","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Qi Zhi Institute Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyi","family":"Tang","sequence":"additional","affiliation":[{"name":"Shanghai Qi Zhi Institute,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University Shanghai Qi Zhi Institute,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Guan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibing","family":"Guan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Distserve: Disaggregating prefill and decoding for goodputoptimized large language model serving","author":"Zhong","year":"2024","journal-title":"OSDI 24"},{"key":"ref2","article-title":"Memserve: Context caching for disaggregated llm serving with elastic memory pool","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv:2406.17565"},{"key":"ref3","article-title":"MILLION: mastering long-context LLM inference via outlier-immunized KV product quantization","author":"Z. W","year":"2025","journal-title":"62nd DAC"},{"key":"ref4","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv preprint arXiv:2210.17323"},{"key":"ref5","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","author":"Xiao","year":"2023","journal-title":"ICML"},{"key":"ref6","article-title":"Qserve: W4a8kv4 quantization and system co-design for efficient 11 m serving","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv:2405.04532"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00082"}],"event":{"name":"2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)","location":"Lantau, Hong Kong","start":{"date-parts":[[2026,1,19]]},"end":{"date-parts":[[2026,1,22]]}},"container-title":["2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11420221\/11420229\/11420766.pdf?arnumber=11420766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T05:37:42Z","timestamp":1773207462000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11420766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":7,"URL":"https:\/\/doi.org\/10.1109\/asp-dac66049.2026.11420766","relation":{},"subject":[],"published":{"date-parts":[[2026,1,19]]}}}