lightmatter-ai / INT-FP-QSimLinks
Flexible simulator for mixed precision and format simulation of LLMs and vision transformers.
☆51Updated 2 years ago
Alternatives and similar repositories for INT-FP-QSim
Users that are interested in INT-FP-QSim are comparing it to the libraries listed below
Sorting:
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆49Updated 3 years ago
- ACL 2023☆39Updated 2 years ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆112Updated last year
- A collection of research papers on efficient training of DNNs☆70Updated 3 years ago
- GPU operators for sparse tensor operations☆35Updated last year
- ☆31Updated last year
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆50Updated 2 years ago
- ☆157Updated 2 years ago
- ☆30Updated last year
- ☆40Updated last year
- Reorder-based post-training quantization for large language model☆199Updated 2 years ago
- Code Repository of Evaluating Quantized Large Language Models☆136Updated last year
- BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.☆58Updated 3 years ago
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆129Updated 2 years ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆172Updated 2 months ago
- ☆74Updated last month
- ☆21Updated 2 years ago
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆67Updated 7 months ago
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆37Updated last year
- AFPQ code implementation☆23Updated 2 years ago
- [TMLR] Official PyTorch implementation of paper "Efficient Quantization-aware Training with Adaptive Coreset Selection"☆36Updated last year
- A framework to compare low-bit integer and float-point formats☆66Updated this week
- This project is the official implementation of our accepted ICLR 2022 paper BiBERT: Accurate Fully Binarized BERT.☆89Updated 2 years ago
- ☆85Updated last year
- ☆52Updated last year
- LLM Inference with Microscaling Format☆34Updated last year
- ☆10Updated 4 years ago
- [ICML2025] KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference☆26Updated 2 weeks ago
- Code for ICML 2021 submission☆35Updated 4 years ago
- Repository for CPU Kernel Generation for LLM Inference☆28Updated 2 years ago