aiha-lab / TernGEMMLinks
TernGEMM: General Matrix Multiply Library with Ternary Weights for Fast DNN Inference
☆13Updated 3 years ago
Alternatives and similar repositories for TernGEMM
Users that are interested in TernGEMM are comparing it to the libraries listed below
Sorting:
- Layer-wise Pruning of Transformer Heads for Efficient Language Modeling☆21Updated 3 years ago
- [ICASSP'22] Integer-only Zero-shot Quantization for Efficient Speech Recognition☆33Updated 3 years ago
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆47Updated 2 years ago
- ☆20Updated last year
- ☆59Updated last year
- ☆15Updated last year
- ☆9Updated 9 months ago
- LLM Inference with Microscaling Format☆23Updated 7 months ago
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆63Updated last year
- Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)☆16Updated 11 months ago
- [NeurIPS 2023] Token-Scaled Logit Distillation for Ternary Weight Generative Language Models☆17Updated last year
- AFPQ code implementation☆21Updated last year
- ☆28Updated 11 months ago
- ☆75Updated 5 months ago
- ☆29Updated this week
- In this repository, we explore model compression for transformer architectures via quantization. We specifically explore quantization awa…☆24Updated 4 years ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆92Updated last year
- [ICLR2025]: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitt…☆61Updated 2 months ago
- ☆22Updated 7 months ago
- ☆51Updated 11 months ago
- [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning☆94Updated 10 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆109Updated 8 months ago
- [ICML'21 Oral] I-BERT: Integer-only BERT Quantization☆250Updated 2 years ago
- ☆39Updated 7 months ago
- ☆10Updated 7 months ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Updated 2 months ago
- A collection of research papers on efficient training of DNNs☆70Updated 2 years ago
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.☆110Updated 6 months ago
- Flexible simulator for mixed precision and format simulation of LLMs and vision transformers.☆50Updated last year
- ☆10Updated 3 years ago