LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

  • Markets
  • Builders
  • Research
  • Ecosystems
  • Launchpads
  • Search
Builders

NVIDIA

yukang

Research Scientist in NVIDIA, working in Efficient and Long AI.

GitHub@yukangchen_Website
Followers
492
Public repos
38
Stars (recent)
7
Ecosystems
1

Projects

Repositories this builder owns.

yukang2017.github.io
Homepage
2
triattention
TriAttention [Official] — Efficient long reasoning with trigonometric KV cache compression. 2.5x throughput, 10.7x KV memory reduction, no accuracy loss.
—
LongLive-Spark-Demo
No description.
1
QeRL
QeRL enables RL for 32B LLMs on a single H100 GPU.
—

Connected narratives

AI AgentsConsumer CryptoSocialFiStablecoinsAgent CommerceOnchain Apps

Related builders

Others building in the same ecosystem.

Jesse Pollak
1.3K followers
0xDeployer
— followers
Xen
— followers
Ahaan Raizada
— followers
Youssef
— followers
Igor Yuzo
— followers
Awesome-Video-LMM-Post-Training
🔥🔥🔥 Latest Papers, Codes and Datasets on Video-LMM Post-Training
2
LongLive
No description.
—
EasyR1
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
1
Long-RL
Long-RL: Scaling RL to Long Sequences
—

Recent activity

Most recently pushed work.

  • yukang2017/yukang2017.github.io
    pushed 5h ago
  • yukang2017/triattention
    pushed 2mo ago
  • yukang2017/LongLive-Spark-Demo
    pushed 7mo ago
  • yukang2017/QeRL
    pushed 8mo ago