Predibase ORG

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Best practices for distilling large language models.

No description.

No description.

A uniform interface to run deep learning models from multiple frameworks

Serving multiple LoRA finetuned LLM as one

No description.

Distributed SQL Engine in Python using Dask

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]

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

The API (CRD) of Volcano

A Cloud Native Batch System (Project under CNCF)

The official Python client for the Huggingface Hub.

LlamaIndex (GPT Index) is a data framework for your LLM applications

⚡ Building applications with LLMs through composability ⚡

Kubernetes Image Puller is used for caching images on a cluster. It creates a DaemonSet downloading and running the relevant container images on each node.

Bump version in Helm Chart.yaml and setup.py files

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

GitHub action for identifying the last successful commit for a given workflow and branch.