Wang
Zongwu
home
archives
categories
tags
Slides
Your browser does not support HTML5 video.
Hi my new friend!
书山有路勤为径,
学海无涯苦作舟。
Home
page
Scroll down
Welcome to Zongwu's Science Hub ✨
Residence:
Shanghai
Age:
18
Contact Me
Architecture
206
Read More
System
58
Read More
Newest Publications
Algorithm
MiniCache_ KV Cache Compression in Depth Dimension for Large Language Models
26/02/20
11:04
Architecture
Mosaic_ Harnessing the Micro-architectural Resources of Servers in Serverless Environments
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
Algorithm
eDKM_An_Efficient_and_Accurate_Train-time_Weight_Clustering_for_Large_Language_Models
26/02/20
11:04
Architecture
FlexLLM_Composable_HLS_Library_for_Flexible_Hybrid_LLM_Accelerator_Design
26/02/20
11:04
1
…
20
21
22
23
24
…
32
Please enter keywords to search