NVIDIA / TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support 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 performant way.
☆10,401Updated this week
Alternatives and similar repositories for TensorRT-LLM:
Users that are interested in TensorRT-LLM are comparing it to the libraries listed below
- SGLang is a fast serving framework for large language models and vision language models.☆13,829Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆6,972Updated this week
- Large Language Model Text Generation Inference☆10,081Updated this week
- Fast and memory-efficient exact attention☆17,192Updated this week
- PyTorch native post-training library☆5,138Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,274Updated this week
- Transformer related optimization, including BERT, GPT☆6,144Updated last year
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,872Updated 9 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,970Updated 3 weeks ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,826Updated 3 weeks ago
- Tensor library for machine learning☆12,445Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,187Updated this week
- Tools for merging pretrained large language models.☆5,614Updated this week
- FlashInfer: Kernel Library for LLM Serving☆2,764Updated this week
- Go ahead and axolotl questions☆9,258Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,136Updated last week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,940Updated 3 weeks ago
- Train transformer language models with reinforcement learning.☆13,559Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,463Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,390Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆18,274Updated this week
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,157Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆46,456Updated this week
- A PyTorch native library for large-scale model training☆3,665Updated this week
- A framework for few-shot evaluation of language models.☆8,815Updated last week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆12,064Updated last week
- Development repository for the Triton language and compiler☆15,447Updated this week
- High-speed Large Language Model Serving for Local Deployment☆8,188Updated 2 months ago
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆11,543Updated this week
- Modeling, training, eval, and inference code for OLMo☆5,560Updated this week