Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Xingchen Liu
Observed name:
Liu, Xingchen
Institutions:
Chinese Academy of Sciences,
Institute of Computing Technology,
University of Chinese Academy of Sciences
Observed institutions:
Chinese Academy of Sciences,
Institute of Computing Technology,
University of Chinese Academy of Sciences
ORCID:
0009-0006-9410-5365
Observed ORCID:
0009-0006-9410-5365
OpenAlex ID:
A5124075352
COCCL: A Collective Communication Library Supporting Easy Integration and Configuration of Customized Compression for Scalable LLM Training
2026
·
Xingchen Liu
, Haoran Kong
, et al.
·
ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
·
3
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
2026
·
Zedong Liu
, Xinyang Ma
, et al.
·
ACM SIGCOMM Conference (SIGCOMM)
ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs
2026
·
Jinwu Yang
, Jiaan Wu
, et al.
·
ACM/IEEE International Symposium on Computer Architecture (ISCA)
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
2026
·
Liu, Zedong
, Ma, Xinyang
, et al.
·
arXiv (Cornell University)
PDF
CCL-D: A High-Precision Diagnostic System for Slow and Hang Anomalies in Large-Scale Model Training
2026
·
Yida Gu
, Fakang Wang
, et al.
·
ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
PDF
Show more works
View as search
Works count:
5
Citation count:
3
H-index:
1
I10-index:
Year
Topic
Type
