Taehyeon Kim's picture

2 18 3

Taehyeon Kim

Kthyeon

·

https://kthyeon.com/

AI & ML interests

LLM Inference: Parallel, Speculative, Instructive Decoding

Recent Activity

upvoted a paper 2 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

upvoted a paper 14 days ago

Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

liked a model 28 days ago

LGAI-EXAONE/K-EXAONE-236B-A23B

View all activity

Organizations

New activity in microsoft/Phi-3-small-8k-instruct about 1 year ago

Getting the error: "triton.runtime.autotuner.OutOfResources: out of resource: shared memory, Required: 180224, Hardware limit: 166912. Reducing block sizes or `num_stages` may help."

#27 opened over 1 year ago by

commented a paper over 1 year ago

Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters

Paper • 2406.16758 • Published Jun 24, 2024 • 20 •