parano

parano's Stars

• ollama/ollama

  Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

  Language:Go101k5935.1k8k

• abi/screenshot-to-code

  Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

  Language:Python64.7k3833317.9k

• backstage/backstage

  Backstage is an open framework for building developer portals

  Language:TypeScript28.6k2336.3k6.1k

• facebookresearch/seamless_communication

  Foundational Models for State-of-the-Art Speech and Text Translation

  Language:Jupyter Notebook11k1423601.1k

• NVIDIA/TensorRT-LLM

  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++8.8k932k1k

• bentoml/BentoML

  The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

  Language:Python7.2k771.1k794

• rany2/edge-tts

  Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

  Language:Python6.5k50239635

• MaartenGr/BERTopic

  Leveraging BERT and c-TF-IDF to create easily interpretable topics.

  Language:Python6.2k531.7k767

• Codium-ai/pr-agent

  🚀CodiumAI PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍

  Language:Python6.2k47338601

• zsviczian/obsidian-excalidraw-plugin

  A plugin to edit and view Excalidraw drawings in Obsidian

  Language:TypeScript4.3k221.8k234

• NVIDIA/NeMo-Guardrails

  NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

  Language:Python4.2k36368403

• unitycatalog/unitycatalog

  Open, Multi-modal Catalog for Data & AI

  Language:Java2.5k49266396

• FasterDecoding/Medusa

  Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

  Language:Jupyter Notebook2.3k3191161

• MeetKai/functionary

  Chat language model that can use tools and interpret the results

  Language:Python1.4k20126113

• stanford-oval/WikiChat

  WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

  Language:Python1.2k1825107

• test-time-training/ttt-lm-pytorch

  Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

  Language:Python1.1k72662

• test-time-training/ttt-lm-jax

  Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

  Language:Python37291430

• readwiseio/obsidian-readwise

  Official Readwise plugin for Obsidian

  Language:TypeScript26195824

• bentoml/BentoVLLM

  Self-host LLMs with vLLM and BentoML

  Language:Python74101012

• bentoml/llm-bench

  Language:Python38955

• bentoml/rag-tutorials

  a series of tutorials implementing rag service with BentoML and LlamaIndex

  Language:Python29435

• bentoml/BentoChatTTS

  Language:Python21601

• bentoml/BentoLMDeploy

  Self-host LLMs with LMDeploy and BentoML

  Language:Python16512

• bentoml/openllm-models

  Language:Python14628

• bentoml/BentoTRTLLM

  Language:Python6411

• bentoml/BentoYolo

  BentoML service of YOLO v8

  Language:Python5601

• bentoml/llm-router

  Multi-LLM Routing API Endpoint with BentoML

  Language:Python4301

• bentoml/BentoMLCLLM

  Language:Python2401

• mlops-club/vscode-bentoml

  Language:TypeScript2200

• bentoml/BentoTGI

  Language:Python1301