#
Lists (1)
Starred repositories
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching
Official implementation of Half-Quadratic Quantization (HQQ)
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
A Lightweight Library for AI Observability
An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Open source platform for the machine learning lifecycle
Python SDK for Llama Stack
SGLang is a fast serving framework for large language models and vision language models.
The Radio Imaging Audio Generator is a Streamlit-based application designed for radio producers and music creators. It combines OpenAI's GPT models with Facebook's MusicGen technology, enabling the…
A toolkit to create optimal Production-readyRetrieval Augmented Generation(RAG) setup for your data
Fine-Tuning Embedding for RAG with Synthetic Data
A Comprehensive Toolkit for High-Quality PDF Content Extraction
A non-official CLI for Llama Index Parser
aider is AI pair programming in your terminal
Composable building blocks to build Llama Apps
vLLM for embedding tasks using Original LLMs (Qwen2, LLaMA)
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
Deploy agents, models, RAG, pipelines and more - without learning MLOps.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4…
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥