Picture for Wenqi Jiang

Wenqi Jiang

MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels

Add code
May 13, 2024
Viaarxiv icon

PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design

Mar 08, 2024
Figure 1 for PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design
Figure 2 for PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design
Figure 3 for PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design
Figure 4 for PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design
Viaarxiv icon

Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models

Add code
Oct 15, 2023
Viaarxiv icon

Co-design Hardware and Algorithm for Vector Search

Add code
Jul 06, 2023
Figure 1 for Co-design Hardware and Algorithm for Vector Search
Figure 2 for Co-design Hardware and Algorithm for Vector Search
Figure 3 for Co-design Hardware and Algorithm for Vector Search
Figure 4 for Co-design Hardware and Algorithm for Vector Search
Viaarxiv icon

Switch Spaces: Learning Product Spaces with Sparse Gating

Feb 17, 2021
Figure 1 for Switch Spaces: Learning Product Spaces with Sparse Gating
Figure 2 for Switch Spaces: Learning Product Spaces with Sparse Gating
Figure 3 for Switch Spaces: Learning Product Spaces with Sparse Gating
Figure 4 for Switch Spaces: Learning Product Spaces with Sparse Gating
Viaarxiv icon

MicroRec: Accelerating Deep Recommendation Systems to Microseconds by Hardware and Data Structure Solutions

Oct 12, 2020
Figure 1 for MicroRec: Accelerating Deep Recommendation Systems to Microseconds by Hardware and Data Structure Solutions
Figure 2 for MicroRec: Accelerating Deep Recommendation Systems to Microseconds by Hardware and Data Structure Solutions
Figure 3 for MicroRec: Accelerating Deep Recommendation Systems to Microseconds by Hardware and Data Structure Solutions
Figure 4 for MicroRec: Accelerating Deep Recommendation Systems to Microseconds by Hardware and Data Structure Solutions
Viaarxiv icon

Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning

Mar 21, 2020
Figure 1 for Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning
Figure 2 for Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning
Figure 3 for Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning
Figure 4 for Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning
Viaarxiv icon