%0 Journal Article %1 journals/corr/abs-2301-12017 %A Wu, Xiaoxia %A Li, Cheng %A Aminabadi, Reza Yazdani %A Yao, Zhewei %A He, Yuxiong %D 2023 %J CoRR %K dblp %T Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases. %U http://dblp.uni-trier.de/db/journals/corr/corr2301.html#abs-2301-12017 %V abs/2301.12017

@article{journals/corr/abs-2301-12017, added-at = {2023-01-31T00:00:00.000+0100}, author = {Wu, Xiaoxia and Li, Cheng and Aminabadi, Reza Yazdani and Yao, Zhewei and He, Yuxiong}, biburl = {https://www.bibsonomy.org/bibtex/2e79e3528fb0ac3de46bf3bc4c3ad083e/dblp}, ee = {https://doi.org/10.48550/arXiv.2301.12017}, interhash = {d38aae27ced66f6ebfa29bbf6ae5bef3}, intrahash = {e79e3528fb0ac3de46bf3bc4c3ad083e}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-09T00:09:01.000+0200}, title = {Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2301.html#abs-2301-12017}, volume = {abs/2301.12017}, year = 2023 }