logo
WangZongwu
Hi my new friend!

书山有路勤为径，
学海无涯苦作舟。

Scroll down
Newest Publications
GPU
Ghost Arbitration——缓解 GPU 互连侧信道定时攻击的安全仲裁机制深度解析
  • 26/02/20
  • 11:04
Algorithm
KV-Latent_ Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding
  • 26/02/20
  • 11:04
Architecture
Mosaic_ Harnessing the Micro-architectural Resources of Servers in Serverless Environments
  • 26/02/20
  • 11:04
Algorithm
MiniCache_ KV Cache Compression in Depth Dimension for Large Language Models
  • 26/02/20
  • 11:04
Architecture
PIM-MMU_A_Memory_Management_Unit_for_Accelerating_Data_Transfers_in_Commercial_PIM_Systems
  • 26/02/20
  • 11:04
Algorithm
ReCalKV_ Low-Rank KV Cache Compression via Head Reordering and Offline Calibration
  • 26/02/20
  • 11:04
System
SCAR_ Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators
  • 26/02/20
  • 11:04
System
SkipDecode_ Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference
  • 26/02/20
  • 11:04
Algorithm
SpikingMamba_ Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba
  • 26/02/20
  • 11:04
Architecture
Warped-Compaction_ Maximizing GPU Register File Bandwidth Utilization via Operand Compaction
  • 26/02/20
  • 11:04
1…1718192021…29
Please enter keywords to search
  • to close