ChenMnZ / INT_vs_FPLinks
A framework to compare low-bit integer and float-point formats
☆54Updated 2 months ago
Alternatives and similar repositories for INT_vs_FP
Users that are interested in INT_vs_FP are comparing it to the libraries listed below
Sorting:
- ☆38Updated last year
- ☆85Updated 11 months ago
- LLM Inference with Microscaling Format☆34Updated last year
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆111Updated last year
- ☆60Updated last year
- The official implementation of the DAC 2024 paper GQA-LUT☆20Updated last year
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆64Updated 6 months ago
- ☆74Updated 3 weeks ago
- ☆24Updated last year
- AFPQ code implementation☆23Updated 2 years ago
- [ICML 2025] SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆47Updated last year
- ☆51Updated last year
- Code for the paper “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling”☆104Updated this week
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆123Updated 6 months ago
- Quantized Attention on GPU☆44Updated last year
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆38Updated last year
- Code Repository of Evaluating Quantized Large Language Models☆136Updated last year
- ☆31Updated last year
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆29Updated 10 months ago
- ☆30Updated last year
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆49Updated 3 years ago
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆55Updated last year
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 9 months ago
- ACL 2023☆39Updated 2 years ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆170Updated last month
- ☆116Updated 7 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆90Updated last year
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- ☆52Updated 7 months ago
- ☆77Updated last year