turboderp-org / exllamav3Links
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
☆626Updated 2 weeks ago
Alternatives and similar repositories for exllamav3
Users that are interested in exllamav3 are comparing it to the libraries listed below
Sorting:
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆1,121Updated 3 weeks ago
- llama.cpp fork with additional SOTA quants and improved performance☆1,605Updated this week
- Web UI for ExLlamaV2☆513Updated last year
- Large-scale LLM inference engine☆1,647Updated 3 weeks ago
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆165Updated last year
- ☆90Updated 2 months ago
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆232Updated 2 months ago
- LLM Frontend in a single html file☆694Updated last month
- ☆135Updated 9 months ago
- Docs for GGUF quantization (unofficial)☆366Updated 6 months ago
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆569Updated last year
- ☆337Updated 6 months ago
- An OpenAI API compatible API for chat with image input and questions about the images. aka Multimodal.☆266Updated 11 months ago
- automatically quant GGUF models☆219Updated last month
- ☆109Updated 5 months ago
- A multimodal, function calling powered LLM webui.☆216Updated last year
- Croco.Cpp is fork of KoboldCPP infering GGML/GGUF models on CPU/Cuda with KoboldAI's UI. It's powered partly by IK_LLama.cpp, and compati…☆156Updated this week
- InferX: Inference as a Service Platform☆156Updated this week
- DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference☆603Updated 2 months ago
- Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.☆49Updated 3 months ago
- Easily view and modify JSON datasets for large language models☆87Updated 8 months ago
- 🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality degradation across Weight-Only Quantiza…☆845Updated this week
- A fast batching API to serve LLM models☆189Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆912Updated last month
- Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc☆2,311Updated last week
- Produce your own Dynamic 3.0 Quants and achieve optimum accuracy & SOTA quantization performance! Input your VRAM and RAM and the toolcha…☆76Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆21Updated this week
- Open source LLM UI, compatible with all local LLM providers.☆177Updated last year
- A local AI companion that uses a collection of free, open source AI models in order to create two virtual companions that will follow you…☆240Updated 3 months ago
- A pipeline parallel training script for LLMs.☆166Updated 9 months ago