Jaeyeon Kim(김재연)
anencore94
Software Engineer @toss | @kubeflow / katib reviewer
Languages
Repos
50
Stars
8
Forks
3
Top Language
Python
Loading contributions...
Top Repositories
convert time series data from dataframe to sliding window
pre-receive hook which checks certain commit convention
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
Standardized Serverless ML Inference Platform on Kubernetes
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
A Knative ingress controller for Istio.
Repositories
50Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
Standardized Serverless ML Inference Platform on Kubernetes
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
A Knative ingress controller for Istio.
A high-throughput and memory-efficient inference and serving engine for LLMs
Kubeflow SDK for ML Experience
Self-hosted huggingface_hub mirror service.
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Kubernetes-based, scale-to-zero, request-driven compute
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Generative AI extensions for onnxruntime
convert time series data from dataframe to sliding window
FastAPI framework, high performance, easy to learn, fast to code, ready for production
🦜🔗 Build context-aware reasoning applications
Open source platform for the machine learning lifecycle
VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of your choice.
Large Language Model Text Generation Inference
Repository for out-of-tree scheduler plugins based on scheduler framework.
My clone repository
Example DRA driver that developers can fork and modify to get them started writing their own.
Dynamic Resource Allocation (DRA) for NVIDIA GPUs in Kubernetes
Machine Learning Toolkit for Kubernetes
Simple Network Testing Tool
pre-receive hook which checks certain commit convention
FastAPI Best Practices and Conventions we used @ hi.peerlink.me
A fork of the simple WireGuard VPN server GUI community maintained
ZenML 🙏: Build portable, production-ready MLOps pipelines. https://zenml.io.
Repository for hyperparameter tuning
Dependency injection framework for Python
No description provided.