Pinned Repositories
load-watcher
Load watcher is a cluster-wide aggregator of metrics, developed for Trimaran: Real Load Aware Scheduler in Kubernetes.
clever
Container Level Energy-efficient VPA Recommender
kepler
Kepler (Kubernetes-based Efficient Power Level Exporter) uses eBPF to probe performance counters and other system stats, use ML models to estimate workload energy consumption based on these stats, and exports them as Prometheus metrics
autoscaler_predictor_model
The data synthesizer, forecaster and predictor model server used together with KEDA scaler or cluster autoscaler to achieve cluster autoscaling with diurnal pattern workload
DoppelGANger
Generating High-fidelity, Synthetic Time Series Datasets with DoppelGANger
Kepler-Demo
Manifests, Documents, Tools used in Kepler Demos
kube-safe-scheduler
OSSNA23Demo
The demo to benchmark energy consumption of FMaaS with GPU energy conservation.
scheduler-plugins
Repository for out-of-tree scheduler plugins based on scheduler framework.
vLLM-DRA
The KubeCon AI day lightning talk to deploy vLLM server using DRA controller by NVIDIA
wangchen615's Repositories
wangchen615/autoscaler_predictor_model
The data synthesizer, forecaster and predictor model server used together with KEDA scaler or cluster autoscaler to achieve cluster autoscaling with diurnal pattern workload
wangchen615/OSSNA23Demo
The demo to benchmark energy consumption of FMaaS with GPU energy conservation.
wangchen615/vLLM-DRA
The KubeCon AI day lightning talk to deploy vLLM server using DRA controller by NVIDIA
wangchen615/Kepler-Demo
Manifests, Documents, Tools used in Kepler Demos
wangchen615/load-watcher
Load watcher is a cluster-wide aggregator of metrics, developed for Trimaran: Real Load Aware Scheduler in Kubernetes.
wangchen615/openheygen
HeyGen's open source solution
wangchen615/trimaran-kubecon24
The demo scripts for Trimaran schedulers presented at KubeCon EU 2024 at Paris.
wangchen615/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
wangchen615/scheduler-plugins
Repository for out-of-tree scheduler plugins based on scheduler framework.
wangchen615/clever
Container Level Energy-efficient VPA Recommender
wangchen615/code-generator
Generators for kube-like API types
wangchen615/DALLE2-pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
wangchen615/dspy
DSPy: The framework for programming—not prompting—foundation models
wangchen615/embedchain
Framework to easily create LLM powered bots over any dataset.
wangchen615/fmperf
wangchen615/kepler
Kepler (Kubernetes-based Efficient Power Level Exporter) uses eBPF to probe energy related system stats and exports as Prometheus metrics
wangchen615/kube-scheduler-simulator
A web-based simulator for the Kubernetes scheduler
wangchen615/kubernetes
Production-Grade Container Scheduling and Management
wangchen615/kubernetes-autoscaler-1
Autoscaling components for Kubernetes
wangchen615/langchain-ask-pdf
An AI-app that allows you to upload a PDF and ask questions about it. It uses OpenAI's LLMs to generate a response.
wangchen615/leaderboard
The leaderboard code for benchmarking LLM models.
wangchen615/llm-sys-class
Docs for LLM System class
wangchen615/magvit
Official JAX implementation of MAGVIT: Masked Generative Video Transformer
wangchen615/secondary-scheduler-operator
Red Hat Certified optional operator for secondary schedulers
wangchen615/Seine-HelloWorld
The testing repo for Seine Bot
wangchen615/sglang
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
wangchen615/test-infra
Test infrastructure for the Kubernetes project.
wangchen615/vllm-router
vLLM Router
wangchen615/wangchen615.github.io
Chen Wang's personal website
wangchen615/wg-env-sustainability
🌳🌍♻️ Environmental Sustainability Working Group