Search results

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.

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.

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

Creating semantic cache to store responses from LLM queries.

GPU cluster manager for running and managing LLMs.

Create customizable UI components around your models.

A curated list of Large Language Model.

Python materials for the online course on diffusion models by @huggingface.

Platform for deploying your Machine Learning to production.

A service for deployment Apache Spark MLLib machine learning models as realtime, batch or reactive web services.

Code for hyperparameter tuning/optimization of machine learning and deep learning algorithms.

Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.

Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.

A python package that integrates an LLM copilot inside the keras model development workflow.

Kubernetes custom resource definition for serving ML models on arbitrary frameworks.

Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.

Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.