turboderp-org / exllamav2
A fast inference library for running LLMs locally on modern consumer-class GPUs
☆4,171Updated this week
Alternatives and similar repositories for exllamav2
Users that are interested in exllamav2 are comparing it to the libraries listed below
Sorting:
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.☆2,874Updated last year
- Large-scale LLM inference engine☆1,419Updated last week
- Go ahead and axolotl questions☆9,368Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,846Updated last month
- Python bindings for llama.cpp☆9,107Updated last week
- 4 bits quantization of LLaMA using GPTQ☆3,051Updated 10 months ago
- Python bindings for the Transformer models implemented in C/C++ using GGML library.☆1,865Updated last year
- Large Language Model Text Generation Inference☆10,119Updated this week
- Tools for merging pretrained large language models.☆5,721Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,162Updated last week
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆950Updated this week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,823Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆7,020Updated this week
- Fast inference engine for Transformer models☆3,797Updated last month
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,005Updated last week
- Tensor library for machine learning☆12,532Updated last week
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,715Updated 5 months ago
- Customizable implementation of the self-instruct paper.☆1,041Updated last year
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,526Updated 10 months ago
- 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading☆9,621Updated 8 months ago
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆2,976Updated last week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,010Updated last month
- PyTorch native post-training library☆5,186Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,886Updated 10 months ago
- INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model☆1,516Updated last month
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,104Updated last year
- ☆2,939Updated 8 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆14,392Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,170Updated 7 months ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,484Updated last year