99991 / pyggufLinks
GGUF parser in Python
☆28Updated last year
Alternatives and similar repositories for pygguf
Users that are interested in pygguf are comparing it to the libraries listed below
Sorting:
- Python bindings for ggml☆146Updated last year
- Simple high-throughput inference library☆127Updated 3 months ago
- llama.cpp to PyTorch Converter☆34Updated last year
- Inference of Mamba models in pure C☆191Updated last year
- Experiments with BitNet inference on CPU☆54Updated last year
- Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs☆110Updated last year
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆13Updated last year
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- QuIP quantization☆58Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆267Updated 10 months ago
- ☆51Updated last year
- ☆217Updated 7 months ago
- ☆85Updated last week
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆155Updated 10 months ago
- ☆49Updated last year
- ☆120Updated last year
- Repository for CPU Kernel Generation for LLM Inference☆26Updated 2 years ago
- RWKV-7: Surpassing GPT☆94Updated 9 months ago
- ☆17Updated last year
- PB-LLM: Partially Binarized Large Language Models☆153Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees" adapted for Llama models☆39Updated 2 years ago
- 1.58-bit LLaMa model☆82Updated last year
- Docker image NVIDIA GH200 machines - optimized for vllm serving and hf trainer finetuning☆47Updated 6 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated 10 months ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆277Updated last year
- ☆38Updated last year
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 6 months ago
- Implementation of nougat that focuses on processing pdf locally.☆81Updated 7 months ago
- Experiments on speculative sampling with Llama models☆128Updated 2 years ago