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.
☆8,604Updated this week
Related projects ⓘ
Alternatives and complementary repositories for TensorRT-LLM
- A high-throughput and memory-efficient inference and serving engine for LLMs☆29,785Updated this week
- SGLang is a fast serving framework for large language models and vision language models.☆5,919Updated this week
- Large Language Model Text Generation Inference☆9,011Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆4,593Updated this week
- Fast and memory-efficient exact attention☆14,109Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆6,244Updated this week
- Transformer related optimization, including BERT, GPT☆5,871Updated 7 months ago
- A framework for few-shot evaluation of language models.☆6,904Updated this week
- PyTorch native finetuning library☆4,267Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,458Updated last month
- Tools for merging pretrained large language models.☆4,788Updated this week
- Train transformer language models with reinforcement learning.☆9,967Updated this week
- Finetune Llama 3.2, Mistral, Phi, Qwen & Gemma LLMs 2-5x faster with 80% less memory☆17,884Updated this week
- Go ahead and axolotl questions☆7,858Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆2,580Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,650Updated 3 months ago
- Ongoing research training transformer models at scale☆10,480Updated this week
- Python bindings for llama.cpp☆8,072Updated this week
- Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom dataset…☆14,903Updated this week
- Retrieval and Retrieval-augmented LLMs☆7,471Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆10,590Updated this week
- 📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batc…☆2,782Updated last week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,498Updated 3 weeks ago
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆3,629Updated last week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆16,354Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆7,835Updated 6 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,028Updated 4 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆8,612Updated this week
- a state-of-the-art-level open visual language model | 多模态预训练模型☆6,062Updated 5 months ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,647Updated 3 weeks ago