VCA-EPFL / FSALinks
FSA: Fusing FlashAttention within a Single Systolic Array
☆50Updated last month
Alternatives and similar repositories for FSA
Users that are interested in FSA are comparing it to the libraries listed below
Sorting:
- An open-source parameterizable NPU generator with full-stack multi-target compilation stack for intelligent workloads.☆66Updated this week
- Multi-core HW accelerator mapping optimization framework for layer-fused ML workloads.☆58Updated 3 months ago
- A systolic array simulator for multi-cycle MACs and varying-byte words, with the paper accepted to HPCA 2022.☆80Updated 3 years ago
- A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching☆63Updated last week
- Open source RTL implementation of Tensor Core, Sparse Tensor Core, BitWave and SparSynergy in the article: "SparSynergy: Unlocking Flexib…☆17Updated 6 months ago
- High-Performance Sparse Linear Algebra on HBM-Equipped FPGAs Using HLS☆95Updated last year
- Open-source Framework for HPCA2024 paper: Gemini: Mapping and Architecture Co-exploration for Large-scale DNN Chiplet Accelerators☆93Updated 5 months ago
- mNPUsim: A Cycle-accurate Multi-core NPU Simulator (IISWC 2023)☆64Updated 9 months ago
- ☆31Updated 10 months ago
- ☆34Updated 4 months ago
- Simulator framework for analysis of performance, energy consumption, area and cost of multi-node multi-chiplet tile-based manycore design…☆70Updated last year
- ☆45Updated last month
- An FPGA accelerator for general-purpose Sparse-Matrix Dense-Matrix Multiplication (SpMM).☆84Updated last year
- H2-LLM: Hardware-Dataflow Co-Exploration for Heterogeneous Hybrid-Bonding-based Low-Batch LLM Inference☆65Updated 5 months ago
- ☆59Updated 6 months ago
- 关于移植模型至gemmini的文档☆30Updated 3 years ago
- MAERI: A DNN accelerator with reconfigurable interconnects to support flexible dataflow (http://synergy.ece.gatech.edu/tools/maeri/)☆66Updated 4 years ago
- ☆35Updated 6 months ago
- An Open-Source Tool for CGRA Accelerators☆74Updated 3 weeks ago
- An MLIR dialect to enable the efficient acceleration of ML model on CGRAs.