Vahe1994 / AQLMLinks
Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852
☆1,296Updated 2 months ago
Alternatives and similar repositories for AQLM
Users that are interested in AQLM are comparing it to the libraries listed below
Sorting:
- ☆1,004Updated 8 months ago
- Training LLMs with QLoRA + FSDP☆1,527Updated 11 months ago
- Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.☆686Updated last year
- Reaching LLaMA2 Performance with 0.1M Dollars☆985Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆881Updated last month
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,610Updated 11 months ago
- ☆558Updated 11 months ago
- Gemma 2B with 10M context length using Infini-attention.☆943Updated last year
- Run Mixtral-8x7B models in Colab or consumer desktops☆2,325Updated last year
- ⚡ 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
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆853Updated 4 months ago
- ☆447Updated last year
- Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch☆1,880Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,254Updated 5 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆702Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,281Updated 7 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆657Updated 5 months ago
- PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily wri…☆1,413Updated this week
- For releasing code related to compression methods for transformers, accompanying our publications☆446Updated 8 months ago
- ☆545Updated 9 months ago
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,203Updated last year
- A simple, performant and scalable Jax LLM!☆1,923Updated this week
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,399Updated last year
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆721Updated last year
- A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI☆770Updated last year
- Serving multiple LoRA finetuned LLM as one☆1,097Updated last year
- PyTorch native quantization and sparsity for training and inference☆2,392Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆905Updated last year
- A pytorch quantization backend for optimum☆991Updated last month
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,635Updated last year