cornell-zhang / llm-datatypes
Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
☆24Updated 8 months ago
Alternatives and similar repositories for llm-datatypes:
Users that are interested in llm-datatypes are comparing it to the libraries listed below
- [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning☆82Updated 6 months ago
- ☆12Updated 9 months ago
- Serpens is an HBM FPGA accelerator for SpMV☆17Updated 7 months ago
- LLM Inference with Microscaling Format☆19Updated 3 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆29Updated this week
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆29Updated 2 months ago
- Torch2Chip (MLSys, 2024)☆51Updated 3 weeks ago
- Official implementation of EMNLP'23 paper "Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?"☆19Updated last year
- ☆19Updated 2 months ago
- DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators☆13Updated 4 months ago
- A graph linear algebra overlay☆51Updated last year
- Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)☆13Updated 8 months ago
- QuickEst repository: Quick Estimation of Quality of Results☆26Updated 6 years ago
- Differentiable Combinatorial Scheduling at Scale (ICML'24). Mingju Liu, Yingjie Li, Jiaqi Yin, Zhiru Zhang, Cunxi Yu.☆19Updated 4 months ago
- ☆11Updated 3 years ago
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆48Updated 2 years ago
- Repository for artifact evaluation of ASPLOS 2023 paper "SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning"☆24Updated 2 years ago
- [ICML 2021] "Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators" by Yonggan Fu, Yonga…☆15Updated 3 years ago
- ☆15Updated 2 years ago
- Hop-Wise Graph Attention for Scalable and Generalizable Learning on Circuits☆26Updated 6 months ago
- ☆32Updated 4 years ago
- ☆91Updated last year
- ☆50Updated 11 months ago
- GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks☆35Updated last year
- HLSyn benchmark for paper "Towards a Comprehensive Benchmark for FPGA Targeted High-Level Synthesis"☆27Updated last year
- ☆39Updated 4 months ago
- ☆39Updated 8 months ago
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆58Updated 11 months ago
- [HPCA 2022] GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design☆35Updated 2 years ago
- An HBM FPGA based SpMV Accelerator☆13Updated 6 months ago