Sharma, Akshat, Ding, Hangliang, Li, Jianping, Dani, Neel, and Zhang, Minjia. MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference. Retrieved from https://par.nsf.gov/biblio/10632221. Web. doi:10.18653/v1/2025.findings-acl.952.

Sharma, Akshat, Ding, Hangliang, Li, Jianping, Dani, Neel, & Zhang, Minjia. MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference. Retrieved from https://par.nsf.gov/biblio/10632221. https://doi.org/10.18653/v1/2025.findings-acl.952

Sharma, Akshat, Ding, Hangliang, Li, Jianping, Dani, Neel, and Zhang, Minjia. "MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference". Country unknown/Code not available: Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.findings-acl.952. https://par.nsf.gov/biblio/10632221.

@article{osti_10632221,
place = {Country unknown/Code not available}, title = {MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference}, url = {https://par.nsf.gov/biblio/10632221}, DOI = {10.18653/v1/2025.findings-acl.952}, abstractNote = {}, journal = {}, publisher = {Association for Computational Linguistics}, author = {Sharma, Akshat and Ding, Hangliang and Li, Jianping and Dani, Neel and Zhang, Minjia}, }