NVIDIA / TensorRT-LLMLinks
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.
☆12,008Updated this week
Alternatives and similar repositories for TensorRT-LLM
Users that are interested in TensorRT-LLM are comparing it to the libraries listed below
Sorting:
- SGLang is a fast serving framework for large language models and vision language models.☆19,718Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,223Updated this week
- Transformer related optimization, including BERT, GPT☆6,338Updated last year
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,698Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,982Updated last week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,324Updated 3 months ago
- Fast and memory-efficient exact attention☆20,280Updated this week
- Large Language Model Text Generation Inference☆10,621Updated last month
- PyTorch native post-training library☆5,576Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,102Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆7,716Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆61,727Updated this week
- Ongoing research training transformer models at scale☆14,082Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,655Updated 2 months ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,977Updated 6 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,261Updated 5 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆5,418Updated this week
- A framework for few-shot evaluation of language models.☆10,488Updated last week
- High-speed Large Language Model Serving for Local Deployment☆8,374Updated 3 months ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,140Updated 2 months ago
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,165Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,883Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMs☆14,954Updated last week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,180Updated this week
- Tools for merging pretrained large language models.☆6,412Updated this week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,650Updated last year
- Train transformer language models with reinforcement learning.☆16,106Updated this week
- The Triton Inference Server provides an optimized cloud and edge inferencing solution.☆9,972Updated this week
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…☆17,996Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,072Updated 4 months ago