arxiv:2401.10862
Ileana Rugina
irugina
ยท
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 hours ago
WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms upvoted a paper 2 days ago
Disaggregated Quantization: Specializing LLM Prefill and Decode published a model 5 days ago
irugina/frozen-twist-staleness