kserve
Yatai
Our great sponsors
kserve | Yatai | |
---|---|---|
3 | 5 | |
3,047 | 762 | |
7.3% | 2.9% | |
9.4 | 6.8 | |
6 days ago | 2 months ago | |
Python | TypeScript | |
Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
kserve
-
Show HN: Software for Remote GPU-over-IP
Inference servers essentially turn a model running on CPU and/or GPU hardware into a microservice.
Many of them support the kserve API standard[0] that supports everything from model loading/unloading to (of course) inference requests across models, versions, frameworks, etc.
So in the case of Triton[1] you can have any number of different TensorFlow/torch/tensorrt/onnx/etc models, versions, and variants. You can have one or more Triton instances running on hardware with access to local GPUs (for this example). Then you can put standard REST and or grpc load balancers (or whatever you want) in front of them, hit them via another API, whatever.
Now all your applications need to do to perform inference is do an HTTP POST (or use a client[2]) for model input, Triton runs it on a GPU (or CPU if you want), and you get back whatever the model output is.
Not a sales pitch for Triton but it (like some others) can also do things like dynamic batching with QoS parameters, automated model profiling and performance optimization[3], really granular control over resources, response caching, python middleware for application/biz logic, accelerated media processing with Nvidia DALI, all kinds of stuff.
[0] - https://github.com/kserve/kserve
[1] - https://github.com/triton-inference-server/server
[2] - https://github.com/triton-inference-server/client
[3] - https://github.com/triton-inference-server/model_analyzer
-
Run your first Kubeflow pipeline
Kubeflow has multiple components: central dashboard, Kubeflow Notebooks to manage Jupyter notebooks, Kubeflow Pipelines for building and deploying portable, scalable machine learning (ML) workflows based on Docker containers, KF Serving for model serving (apparently superseded by KServe), Katib for hyperparameter tuning and model search, and training operators such as TFJob for training TF models on Kubernetes.
-
[D] Serverless solutions for GPU inference (if there's such a thing)
If you can run on Kubernetes then KFServing is an open source solution that allows for GPU inference and is built upon Knative to allow scale to zero for GPU based inference. From release 0.5 it also has capabilities for multi-model serving as a alpha feature to allow multiple models to share the same server (and via NVIDIA Triton the same GPU).
Yatai
- Show HN: ML Serving orchestration framework on Kubernetes
- Show HN: Yatai: Production-first ML platform on Kubernetes
-
Hello from BentoML
And when you deploy this bento to Kubernetes using Yatai (https://github.com/bentoml/yatai). Yatai will automatically deploy this as microservices. We are working on adding better support for serialization and deserialization support between those microservices to reduce latency cost.
-
[P] Introducing BentoML 1.0 - A faster way to ship your models to production
Introducing Yatai for BentoML: Production-first ML platform on Kubernetes
- Yatai: Model Deployment at Scale on Kubernetes
What are some alternatives?
kubeflow - Machine Learning Toolkit for Kubernetes
BentoML - The most flexible way to serve AI/ML models in production - Build Model Inference Service, LLM APIs, Inference Graph/Pipelines, Compound AI systems, Multi-Modal, RAG as a Service, and more!
aws-virtual-gpu-device-plugin - AWS virtual gpu device plugin provides capability to use smaller virtual gpus for your machine learning inference workloads
sdk-javascript - The official JavaScript SDK for the Modzy Machine Learning Operations (MLOps) Platform.
awesome-mlops - A curated list of references for MLOps
hongbomiao.com - A personal research and development (R&D) lab that facilitates the sharing of knowledge.
kind - Kubernetes IN Docker - local clusters for testing Kubernetes
seldon-core - An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
kubeflow-learn
gallery - BentoML Example Projects 🎨
Python-Schema-Matching - A python tool using XGboost and sentence-transformers to perform schema matching task on tables.
awesome-mlops - :sunglasses: A curated list of awesome MLOps tools