OOCO: Latency-disaggregated Architecture for Online-Offline Co-locate LLM Serving
Paper • 2511.21862 • Published • 1
Zihan Tang
tzh21
AI & ML interests
None yet
Recent Activity
upvoted a paper about 19 hours ago
OOCO: Latency-disaggregated Architecture for Online-Offline Co-locate LLM Serving upvoted a paper about 19 hours ago
xLLM Technical Report upvoted a paper about 19 hours ago
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR InferenceOrganizations
None yet