turboderp-org / exllamav2Links
A fast inference library for running LLMs locally on modern consumer-class GPUs
☆4,239Updated last 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.☆2,887Updated last year
- Large-scale LLM inference engine☆1,481Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,902Updated 3 months ago
- Python bindings for the Transformer models implemented in C/C++ using GGML library.☆1,871Updated last year
- Tools for merging pretrained large language models.☆6,053Updated last week
- Python bindings for llama.cpp☆9,353Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,216Updated 2 months ago
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆1,011Updated this week
- 4 bits quantization of LLaMA using GPTQ☆3,059Updated last year
- Large Language Model Text Generation Inference☆10,352Updated this week
- Go ahead and axolotl questions☆9,985Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,169Updated 9 months ago
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,936Updated last year
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆3,327Updated 2 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆7,330Updated this week
- Fast inference engine for Transformer models☆3,913Updated 3 months ago
- Chat language model that can use tools and interpret the results☆1,572Updated this week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,843Updated last year
- Customizable implementation of the self-instruct paper.☆1,046Updated last year
- High-speed Large Language Model Serving for Local Deployment☆8,236Updated 5 months ago
- Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?☆1,708Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,148Updated last year
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,654Updated last year
- This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?☆1,192Updated 2 weeks ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,172Updated last week
- INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model☆1,533Updated 4 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,040Updated 3 weeks ago
- PyTorch native post-training library☆5,361Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,033Updated 3 months ago
- Training LLMs with QLoRA + FSDP☆1,494Updated 8 months ago