Aditya Desai

activity

20202026

most citedScissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

11 citations · 15 across the 13 of their papers we have counts for

collaborators

Showing 2022Show all

2 papers · 1 filter

cs.LG2022

The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)

Aditya Desai, Anshumali Shrivastava

Embedding tables dominate industrial-scale recommendation model sizes, using up to terabytes of memory. A popular and the largest publicly available machine learning MLPerf benchma…

cs.LG2022

Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing

Aditya Desai, Keren Zhou, Anshumali Shrivastava

Advancements in deep learning are often associated with increasing model sizes. The model size dramatically affects the deployment cost and latency of deep models. For instance, mo…

The trade-offs of model size in large recommendation models : A 10000 × compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)

Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing

The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)