Jiale Chen

softmax

·

AI & ML interests

None yet

Recent Activity

authored a paper about 13 hours ago

WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms

upvoted a paper about 19 hours ago

WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms

upvoted a paper 2 days ago

Disaggregated Quantization: Specializing LLM Prefill and Decode

View all activity

Organizations

Papers 10

arxiv:2609.38121

arxiv:2607.27042

arxiv:2512.00956

arxiv:2507.18553

models 2

softmax/falcon-180B-chat-marlin

Text Generation • 26B • Updated Mar 21, 2024 • 19

softmax/Llama-2-70b-chat-hf-marlin

Text Generation • 10B • Updated Mar 17, 2024 • 17

datasets 0

None public yet