Our great sponsors
-
postgresml
The GPU-powered AI application database. Get your app to market faster using the simplicity of SQL and the latest NLP, ML + LLM models.
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
mosec
A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine
-
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!
To get any real insights, you'd have to benchmark every single line of the prediction function (called "api") to see where the slowdown is actually coming from https://github.com/postgresml/postgresml/blob/15c8488ade86b0...
Everything else is just speculation.
Related posts
- Detect, Defend, Prevail: Payments Fraud Detection using ML & Deepchecks
- Introduction to NannyML: Model Evaluation without labels
-
modeldb VS cascade - a user suggested alternative
2 projects | 12 Dec 2023
-
Sacred VS cascade - a user suggested alternative
2 projects | 5 Dec 2023
-
keepsake VS cascade - a user suggested alternative
2 projects | 5 Dec 2023