cornell-zhang / llm-datatypes
Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
☆24Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for llm-datatypes
- Repository for artifact evaluation of ASPLOS 2023 paper "SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning"☆23Updated last year
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆17Updated last week
- Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)☆12Updated 4 months ago
- QuickEst repository: Quick Estimation of Quality of Results☆26Updated 6 years ago
- DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators☆14Updated last month
- ☆12Updated last year
- ☆40Updated 7 months ago
- mixed-precision quantization for LLMs☆14Updated last year
- [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning☆76Updated 2 months ago
- ☆25Updated 3 years ago
- ☆15Updated 2 years ago
- TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆21Updated last month
- ☆11Updated 3 years ago
- ☆31Updated 3 years ago
- [ICML 2021] "Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators" by Yonggan Fu, Yonga…☆15Updated 2 years ago
- ☆80Updated last year
- ☆34Updated 4 months ago
- A reference implementation of the Mind Mappings Framework.☆28Updated 2 years ago
- Differentiable Combinatorial Scheduling at Scale (ICML'24). Mingju Liu, Yingjie Li, Jiaqi Yin, Zhiru Zhang, Cunxi Yu.☆17Updated 3 weeks ago
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆53Updated 8 months ago
- GoldenEye is a functional simulator with fault injection capabilities for common and emerging numerical formats, implemented for the PyTo…☆22Updated 3 weeks ago
- ☆87Updated 4 months ago
- ☆22Updated last year
- Graph-learning assisted instruction vulnerability estimation published in DATE 2020☆13Updated 3 years ago
- ☆20Updated this week
- Open-source artifacts and codes of our MICRO'23 paper titled “Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi…☆32Updated last year
- ☆20Updated last week
- ☆17Updated 3 years ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆44Updated 5 months ago
- AIM: Accelerating Arbitrary-precision Integer Multiplication on Heterogeneous Reconfigurable Computing Platform Versal ACAP (Full Paper a…☆21Updated last month