Search results

FeatherCNN is a high performance inference engine for convolutional neural networks.

An enterprise-grade, high performance feature store.

Feature Stores for ML provides machine-learning models, research, training resources, or evaluation tools.

A Virtual Feature Store. Turn your existing data infrastructure into a feature store.

Open-source project that provides machine-learning models, research, training resources, or evaluation tools.

PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.

Ultravox is a real-time voice AI infrastructure layer that powers fast, natural, and scalable voice agents.

Ultravox is a real-time voice AI infrastructure layer that powers fast, natural, and scalable voice agents.

Running large language models on a single GPU for throughput-oriented scenarios. (Archived).

Drag & drop UI to build your customized LLM flow using LangchainJS.

Library for high performance deep learning inference on NVIDIA GPUs.

Open-source self-hostable end-to-end LLMOps platform unifying tracing, evals, simulations, datasets, gateway, and guardrails.

Production-grade SDK for observability, automated evaluations and prompt management with sub-100ms guardrails for LLM/agent workflows.

Host inference APIs, bulk inference and fine tune text, vision, audio and multi-modal models.

Testing framework dedicated to ML models, from tabular to LLMs. Detect risks of biases, performance issues and errors in 4 lines of code.

Cloud-Native LLM Routing Engine. Improve LLM app resilience and speed.

Open Bilingual Pre-Trained Model (ICLR 2023).

Open Bilingual Pre-Trained Model, quantization of ChatGLM-130B, can run on consumer-level GPUs.

Google tool for building, testing, and experimenting with Gemini prompts, models, and API workflows.

Google tool for building, testing, and experimenting with Gemini prompts, models, and API workflows.

gotoHuman provides machine-learning models, research, training resources, or evaluation tools.

Implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Creating semantic cache to store responses from LLM queries.

Real-time GPU cloud price comparison across 30+ providers.