Skip to content
View Hiro208's full-sized avatar
  • New York, NY

Block or report Hiro208

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Hiro208/README.md

Hi, I'm Guangjian (Jayden) Dong 👋

M.S. in Data Science at NYU, working on LLM inference serving and GPU / cluster infrastructure. Contributor to the vLLM ecosystem.

🔧 Projects

🌱 Open source: 9 merged PRs

vLLM-Omni (4) · AIBrix (3) · Semantic Router (2)

📄 Publications

  • ReKV: Overlapping Quantized KV Transfer and Suffix Recomputation: ICASSP 2027 (under review)
  • Motion Recency Maps for Zero-Shot Traffic Accident Localisation: CVPR 2026 AUTOPILOT Workshop

🧰 Stack

Languages Python Go Java C++ JavaScript TypeScript CUDA SQL
LLM inference vLLM SGLang AIBrix Semantic Router Mooncake PD Disaggregation KV Cache Quantization Speculative Decoding FP8
GPU & cluster CUDA Kernels Triton NCCL InfiniBand RDMA Nsight Systems Nsight Compute Kubernetes Volcano Slurm
LLM & agents LangGraph MCP Function Calling Multi-Agent Orchestration RAG Embeddings Reranking LLM Evals Guardrails
ML PyTorch MMDiT DINOv2 LoRA Hugging Face
Backend & data REST APIs Spring Boot FastAPI Node.js React PostgreSQL MySQL MongoDB Redis Kafka
Cloud & DevOps AWS (EC2, EKS, Lambda, API Gateway, S3, IAM) Docker Terraform GitHub Actions CI/CD Linux

Pinned Loading

  1. vllm-project/vllm-omni vllm-project/vllm-omni Public

    A framework for efficient model inference with omni-modality models

    Python 7.9k 2.2k

  2. sglang-inference-optimization sglang-inference-optimization Public

    SGLang inference optimization: CUDA fusion, scheduling and audited serving benchmarks

    Python

  3. vllm-project/semantic-router vllm-project/semantic-router Public

    An open, programmable decision layer for models and compute.

    Go 6.5k 1.1k

  4. research-agent-framework research-agent-framework Public

    Agent framework for long-horizon research: multi-turn function calling, sub-agent retrieval, hybrid search with reranking, citation verification, human-in-the-loop

    Python

  5. vllm-project/aibrix vllm-project/aibrix Public

    Cost-efficient and pluggable Infrastructure components for GenAI inference

    Go 5.2k 768

  6. cold-chain-monitor cold-chain-monitor Public

    Cold-chain reefer monitoring: Go REST API, Kafka ingest, Redis live state, breach alerts in ~2 s, on EKS

    Go