688636
event
1772490060
1773263276
<![CDATA[Ph.D. Proposal Oral Exam - Akshat Ramachandran]]>
Title: Co-Designing Hardware And Algorithms For Efficient Foundational Model Computing Via Adaptable Sparsity And QuantizationCommittee:
Dr. Krishna, Advisor
Dr. Lin, Chair
Dr. Qureshi
Dr. Falsafi
Dr. Kundu
]]>
-
-
The objective of this research is to enable efficient and accurate foundation model inference through cross-layer co-optimization of algorithms and hardware across a continuum of granularities—from static, model-centric strategies to dynamic, token-centric execution—leveraging flexible sparsity and quantization techniques.]]>
-
-
-
-
-
-
-
-
<![CDATA[]]>
-
-
-
https://gatech.zoom.us/j/97215734709?pwd=bwZb1k4MOpTabr9akN0zSlTNu6TpCU.1&from=addon
- 434371
-
1788
-
102851
-
1808