Vahe1994 / AQLM
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
☆1,210Updated last month
Alternatives and similar repositories for AQLM:
Users that are interested in AQLM are comparing it to the libraries listed below
- ☆920Updated this week
- Training LLMs with QLoRA + FSDP☆1,440Updated 2 months ago
- Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.☆687Updated 5 months ago
- Reaching LLaMA2 Performance with 0.1M Dollars☆967Updated 6 months ago
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,105Updated 8 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆736Updated 2 weeks ago
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,486Updated 3 months ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆928Updated 3 weeks ago
- ☆517Updated 3 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆1,911Updated last week
- Large-scale LLM inference engine☆1,252Updated this week
- A simple, performant and scalable Jax LLM!☆1,597Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆881Updated this week
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,359Updated 9 months ago
- PyTorch native quantization and sparsity for training and inference☆1,783Updated this week
- Minimalistic large language model 3D-parallelism training☆1,400Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆689Updated 4 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆404Updated last week
- A PyTorch native library for large model training☆3,200Updated this week
- Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch☆1,747Updated last week
- Run Mixtral-8x7B models in Colab or consumer desktops☆2,295Updated 9 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,182Updated 3 months ago
- [NeurIPS'24 Spotlight, ICLR'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which r…☆890Updated this week
- Advanced Quantization Algorithm for LLMs/VLMs.☆352Updated this week
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆358Updated 11 months ago
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,155Updated 3 months ago
- [ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling☆1,588Updated 6 months ago
- Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"☆833Updated last week
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆845Updated 2 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,393Updated 7 months ago