NVIDIA / TensorRT-LLMLinks
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.
☆11,801Updated 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.☆18,897Updated this week
- Transformer related optimization, including BERT, GPT☆6,320Updated last year
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,650Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,146Updated last week
- Large Language Model Text Generation Inference☆10,566Updated last month
- FlashInfer: Kernel Library for LLM Serving☆3,911Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆7,647Updated 2 weeks ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,305Updated 2 months ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,965Updated 6 months ago
- Fast and memory-efficient exact attention☆19,864Updated last week
- High-speed Large Language Model Serving for Local Deployment☆8,363Updated 2 months ago
- Ongoing research training transformer models at scale☆13,824Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,799Updated this week
- Development repository for the Triton language and compiler☆17,218Updated this week
- PyTorch native post-training library☆5,535Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,121Updated last month
- A high-throughput and memory-efficient inference and serving engine for LLMs☆59,817Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆5,282Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,256Updated 5 months ago
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,166Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,088Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,067Updated 3 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,642Updated last year
- A framework for few-shot evaluation of language models.☆10,303Updated last week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,598Updated last month
- Go ahead and axolotl questions☆10,592Updated this week
- Tensor library for machine learning☆13,261Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆8,559Updated 3 weeks ago
- The Triton Inference Server provides an optimized cloud and edge inferencing solution.☆9,879Updated this week
- Efficient Triton Kernels for LLM Training☆5,738Updated this week