ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
Paper • 2607.00466 • Published • 31
Taeho Hwang
doubleyyh
AI & ML interests
None yet
Recent Activity
upvoted a paper 7 days ago
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving reacted to sergiopaniego's post with 🚀 5 months ago
TRL v0.27.0 is out!! 🥳
It includes GDPO, the latest variant of GRPO for multi-reward RL ✨
GDPO decouples reward normalization to avoid reward collapse and improve per-reward convergence — developed by
@sliuau @SimonX et al.
Explore the paper: https://huggingface.co/papers/2601.05242
Explore the full set of changes here:
https://github.com/huggingface/trl/releases/tag/v0.27.0Organizations
upvoted a paper 7 days ago
reacted to sergiopaniego's post with 🚀 5 months ago
Post
956
TRL v0.27.0 is out!! 🥳
It includes GDPO, the latest variant of GRPO for multi-reward RL ✨
GDPO decouples reward normalization to avoid reward collapse and improve per-reward convergence — developed by
@sliuau @SimonX et al.
Explore the paper: GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization (2601.05242)
Explore the full set of changes here:
https://github.com/huggingface/trl/releases/tag/v0.27.0
It includes GDPO, the latest variant of GRPO for multi-reward RL ✨
GDPO decouples reward normalization to avoid reward collapse and improve per-reward convergence — developed by
@sliuau @SimonX et al.
Explore the paper: GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization (2601.05242)
Explore the full set of changes here:
https://github.com/huggingface/trl/releases/tag/v0.27.0
liked a
Space 5 months ago
upvoted a paper 8 months ago
liked a
model 9 months ago
upvoted a paper 9 months ago
upvoted a collection 9 months ago
upvoted a paper 9 months ago
Regarding Instruction Following SFT dataset.
1
#22 opened 12 months ago
by doubleyyh
upvoted a paper about 1 year ago
authored 2
papers over 1 year ago
Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations
Paper • 2404.13948 • Published • 2
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding
Paper • 2502.05609 • Published • 18
upvoted 3
papers over 1 year ago
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding
Paper • 2502.05609 • Published • 18
Revisiting In-Context Learning with Long Context Language Models
Paper • 2412.16926 • Published • 32
VideoRAG: Retrieval-Augmented Generation over Video Corpus
Paper • 2501.05874 • Published • 74
authored a
paper over 1 year ago
updated 2
models over 1 year ago
upvoted a paper over 1 year ago