Junda Chen's picture

1 1 9

Junda Chen

GindaChen

·

https://github.com/GindaChen/

AI & ML interests

Reasoning System

Recent Activity

authored a paper 8 days ago

DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

authored a paper 8 days ago

Mnemosyne: Parallelization Strategies for Efficiently Serving Multi-Million Context Length LLM Inference Requests Without Approximations

authored a paper 8 days ago

Efficiently Serving LLM Reasoning Programs with Certaindex

View all activity

Organizations

GindaChen's activity

authored 3 papers 8 days ago

DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

Paper • 2401.09670 • Published Jan 18, 2024

Mnemosyne: Parallelization Strategies for Efficiently Serving Multi-Million Context Length LLM Inference Requests Without Approximations

Paper • 2409.17264 • Published Sep 25, 2024

Efficiently Serving LLM Reasoning Programs with Certaindex

Paper • 2412.20993 • Published Dec 30, 2024 • 35

upvoted a paper about 1 month ago

Efficiently Serving LLM Reasoning Programs with Certaindex

Paper • 2412.20993 • Published Dec 30, 2024 • 35