Agora-Lab-AI / BitNet-a4.8Links
BitNet a4.8 Implementation in one file of pytorch
☆19Updated last year
Alternatives and similar repositories for BitNet-a4.8
Users that are interested in BitNet-a4.8 are comparing it to the libraries listed below
Sorting:
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆112Updated last year
- Tiny ASIC implementation for "The Era of 1-bit LLMs All Large Language Models are in 1.58 Bits" matrix multiplication unit☆175Updated last year
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆155Updated last year
- [ICML 2024] BiLLM: Pushing the Limit of Post-Training Quantization for LLMs☆229Updated last year
- 0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" i…☆311Updated last year
- PB-LLM: Partially Binarized Large Language Models☆157Updated 2 years ago
- QuIP quantization☆61Updated last year
- The homepage of OneBit model quantization framework.☆200Updated last year
- ACL 2023☆39Updated 2 years ago
- Experimental BitNet Implementation☆73Updated 2 months ago
- ☆70Updated last year
- Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs☆110Updated 2 years ago
- Official implementation for Training LLMs with MXFP4☆118Updated 9 months ago
- ☆118Updated 3 weeks ago
- Repository for CPU Kernel Generation for LLM Inference☆27Updated 2 years ago
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆327Updated 2 months ago
- ☆157Updated 2 years ago
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆37Updated 3 months ago
- ☆163Updated 7 months ago
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆18Updated last year
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆184Updated 10 months ago
- A large-scale RWKV v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy…☆47Updated 3 months ago
- Official PyTorch implementation of "GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance" (ICML 2025)☆50Updated 7 months ago
- Reorder-based post-training quantization for large language model☆199Updated 2 years ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆280Updated 2 years ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆201Updated last year
- Train your own small bitnet model☆77Updated last year
- Work in progress.☆79Updated 2 months ago
- RWKV-7: Surpassing GPT☆104Updated last year
- Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels☆113Updated 2 years ago