Toward a Holistic Performance Evaluation of Large Language Models Across Diverse AI Accelerators.
Murali EmaniSam ForemanVaruni SastryZhen XieSiddhisanket RaskarWilliam ArnoldRajeev ThakurVenkatram VishwanathMichael E. PapkaSanjif ShanmugaveluDarshan GandhiHengyu ZhaoDun MaKiran RanganathRick WeisnerJiunn-yeu ChenYuting YangNatalia VassilievaBin C. ZhangSylvia HowlandAlexander TsyplikhinPublished in: IPDPS (Workshops) (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- language modelling
- query expansion
- speech recognition
- information retrieval
- retrieval model
- statistical language models
- test collection
- context sensitive
- smoothing methods
- term dependencies
- language models for information retrieval
- ad hoc information retrieval
- word error rate
- machine learning
- document ranking
- query specific
- relevance model
- vector space model
- decision trees
- error rate
- pseudo relevance feedback
- pseudo feedback
- query terms
- okapi bm
- question answering