vsingh-group / FrameQuantLinks
☆10Updated last year
Alternatives and similar repositories for FrameQuant
Users that are interested in FrameQuant are comparing it to the libraries listed below
Sorting:
- LLM Inference with Microscaling Format☆34Updated last year
- ☆31Updated last year
- This repository contains the training code of ParetoQ introduced in our work "ParetoQ Scaling Laws in Extremely Low-bit LLM Quantization"☆118Updated 3 months ago
- ☆85Updated last year
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆68Updated last year
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆123Updated 7 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆281Updated 3 months ago
- ☆21Updated 2 years ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆120Updated last year
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆165Updated 2 months ago
- Explore training for quantized models☆26Updated 6 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆93Updated last year
- ☆40Updated last year
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆112Updated last year
- ☆60Updated last year
- ☆44Updated 2 years ago
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆49Updated 3 years ago
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆29Updated 11 months ago
- ☆74Updated last month
- ☆77Updated last year
- ☆52Updated last year
- Transformers components but in Triton☆34Updated 8 months ago
- ☆158Updated 11 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆134Updated last year
- AFPQ code implementation☆23Updated 2 years ago
- ☆30Updated last year
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆172Updated 2 months ago
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆56Updated last year
- ☆25Updated last year
- ☆36Updated last year