Hanshi's picture

Hanshi

preminstrel

·

https://preminstrel.com

AI & ML interests

ML

Recent Activity

upvoted a paper 1 day ago

AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs

upvoted a paper 5 months ago

MMGR: Multi-Modal Generative Reasoning

new activity 8 months ago

ByteDance-Seed/cudaLLM-8B:What is the meaning of "Bo"?

View all activity

Organizations

authored 2 papers over 1 year ago

Fast Best-of-N Decoding via Speculative Rejection

Paper • 2410.20290 • Published Oct 26, 2024 • 10

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

Paper • 2410.21465 • Published Oct 28, 2024 • 11

authored a paper about 2 years ago

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Paper • 2404.11912 • Published Apr 18, 2024 • 17