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
☆1,286Updated 3 weeks ago
Alternatives and similar repositories for AQLM
Users that are interested in AQLM are comparing it to the libraries listed below
Sorting:
- ☆997Updated 6 months ago
- Training LLMs with QLoRA + FSDP☆1,526Updated 9 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☆988Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆868Updated 2 weeks ago
- A simple, performant and scalable Jax LLM!☆1,885Updated this week
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,591Updated 10 months ago
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,168Updated 10 months ago
- Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch☆1,870Updated 2 weeks ago
- ☆554Updated 10 months ago
- Run Mixtral-8x7B models in Colab or consumer desktops☆2,315Updated last year
- Gemma 2B with 10M context length using Infini-attention.☆947Updated last year
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆842Updated 3 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆703Updated last year
- For releasing code related to compression methods for transformers, accompanying our publications☆441Updated 7 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,273Updated 5 months ago
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,193Updated last year
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,235Updated 3 months ago
- ☆446Updated last year
- Large-scale LLM inference engine☆1,530Updated this week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,852Updated last year
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆652Updated 4 months ago
- ☆864Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,229Updated last month
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,606Updated last year
- Mamba-Chat: A chat LLM based on the state-space model architecture 🐍☆928Updated last year
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆710Updated last year
- ☆546Updated 8 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆907Updated 4 months ago
- Train Models Contrastively in Pytorch☆741Updated 5 months ago