sIncerass / QBERTLinks
☆15Updated 2 years ago
Alternatives and similar repositories for QBERT
Users that are interested in QBERT are comparing it to the libraries listed below
Sorting:
- Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs☆27Updated last year
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆48Updated 2 years ago
- ☆68Updated last year
- ☆19Updated 3 years ago
- BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization (ICLR 2021)☆41Updated 4 years ago
- A collection of research papers on efficient training of DNNs☆69Updated 3 years ago
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆64Updated last year
- ☆14Updated last year
- Training with Block Minifloat number representation☆16Updated 4 years ago
- The official implementation of the DAC 2024 paper GQA-LUT☆20Updated 8 months ago
- [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning☆101Updated last year
- [ICML 2021] "Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators" by Yonggan Fu, Yonga…☆16Updated 3 years ago
- Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)☆20Updated last year
- Post-training sparsity-aware quantization☆34Updated 2 years ago
- Neural Network Quantization With Fractional Bit-widths☆12Updated 4 years ago
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆113Updated last month
- Adaptive floating-point based numerical format for resilient deep learning☆14Updated 3 years ago
- DeiT implementation for Q-ViT☆24Updated 4 months ago
- LLM Inference with Microscaling Format☆29Updated 9 months ago
- Torch2Chip (MLSys, 2024)☆53Updated 4 months ago
- ☆29Updated this week