Peng,
Andy
Toggle navigation
about
bio
blog
(current)
publications
projects
cv
LLM Open Source Programs 2025 May
Created in May, 2025
2025
·
LLM
opensource
·
products
Prompt Caching / KV Cache
LMCache
How LMCache Turbocharges Enterprise LLM Inference Frameworks
LMCache x Mooncake: Unite to Pioneer KVCache-Centric LLM Serving System
Mooncake
Inference
llm-d
Introducing the next generation of AI inference, powered by llm-d
Dynamo
NVIDIA Dynamo Adds GPU Autoscaling, Kubernetes Automation, and Networking Optimizations
Beyond the Algorithm with NVIDIA: Introducing NVIDIA Dynamo
SGLang
Deploying DeepSeek with PD Disaggregation and Large-Scale Expert Parallelism on 96 H100 GPUs
vLLM
Agentic AI
Strands Agents (
blog
,
GitHub
)