A high-throughput and memory-efficient inference and serving engine for LLMs
Repository Index
47,133 repositories indexed
1–17 of 17 · Most stars
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
- adapter
- diffusion
- llm
- parameter-efficient-learning
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
Nano vLLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
- gpt-2
- adaptation
- language-model
- gpt-3
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
- bert
- sentence-encoding
- deep-learning
- clip-model
Low-code framework for building custom LLMs, neural networks, and other AI models
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
- healthcare
- data-mining
- deep-learning
- preprocessing
Pretrained model hub for Keras 3.
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a platform for autonomous architecture research.
- auto-research
- benchmark
- deep-learning
- language-models
MCP server for spatial transcriptomics analysis through natural language interfaces.
- bioinformatics
- cell-communication
- deconvolution
- machine-learning
A minimalistic codebase for training NLG models from HuggingFace Transformers using PyTorch Lightning.
- bart
- generation
- gpt-2
- language-model