KaisennHu/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
M.Eng in CS @ HUST | Software Engineer @ Huawei | Research: Distributed Systems · Serverless · AI Systems
Repositories
KaisennHu/router
A high-performance and light-weight router for vLLM large scale deployment
KaisennHu/KaisennHu
KaisennHu/dynamo
A Datacenter Scale Distributed Inference Serving Framework
KaisennHu/agent-infer
vLLM based inference framework for agentic workload.
KaisennHu/ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
KaisennHu/ray-ascend
KaisennHu/verl-omni
RL training framework for diffusion and omni-modality models
KaisennHu/verl
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
KaisennHu/AReaL
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
KaisennHu/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
KaisennHu/TransferQueue
An asynchronous streaming data management module for efficient post-training.
KaisennHu/yr_vllm_launcher
KaisennHu/multi-rl-task-scheduler
This is the design and implement of multi RL task pool-scheduler
KaisennHu/monarch
PyTorch Single Controller