Skip to content
View kube-gopher's full-sized avatar
🎯
Focusing
🎯
Focusing
1 follower · 8 following
  • ChengDu,China
  • 05:33 (UTC +08:00)

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Block or report kube-gopher

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
kube-gopher/README.md

Hi there 👋

I focus on building cloud-native AI inference infrastructure — making LLM serving on Kubernetes declarative, autoscaling, and scale-to-zero.

2 years of SRE (Prometheus, multi-cloud) before this — I bring that operational lens to a stack where GPUs and inference engines are still black boxes.

  • 🔥 Building Hearth — a vendor-neutral K8s operator for scale-to-zero serving of open-source LLMs (Qwen / DeepSeek / GLM),with NVIDIA / Ascend as pluggable backends. Verified end-to-end on real GPUs.
  • 🧰 Focus: queue-driven autoscaling, cold-start UX, model caching, observability
  • 📫 jzlyy68@gmail.com

Pinned Loading

  1. hearth-project/hearth hearth-project/hearth Public

    Declarative, scale-to-zero LLM serving on Kubernetes — vendor-neutral.

    Go 4 5

  2. volcano-sh/volcano volcano-sh/volcano Public

    A Cloud Native Batch System (Project under CNCF)

    Go 5.7k 1.4k

  3. volcano-sh/kthena volcano-sh/kthena Public

    Kubernetes-native AI serving platform for scalable model serving.

    Go 365 130