Bingyang Wu
4 papers · 2023–2026 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
Top co-authors
Research topics
Keywords
large language model
(2)
inference serving
(2)
gpu utilization
(2)
low-rank adaptation
(1)
throughput optimization
(1)
training throughput
(1)
stage fusion
(1)
preemptive scheduling
(1)
deep learning workload
(1)
adapter merging
(1)
rate control
(1)
credit-based batching
(1)
request migration
(1)
gpu sharing
(1)
container cloud
(1)
transparent memory
(1)
multi-level feedback queue
(1)
autoregressive generation
(1)
gpu memory management
(1)
reinforcement learning from human feedback
(1)
Papers
FastServe: Iteration-Level Preemptive Scheduling for Large Language Model Inference
NSDI 2026
Optimizing RLHF Training for Large Language Models with Stage Fusion
NSDI 2025
dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving
OSDI 2024
Transparent GPU Sharing in Container Clouds for Deep Learning Workloads
NSDI 2023