mit-han-lab / spatten
[HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
☆75Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for spatten
- ☆40Updated 3 years ago
- [HPCA 2023] ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design☆97Updated last year
- [TCAD'23] AccelTran: A Sparsity-Aware Accelerator for Transformers☆33Updated 11 months ago
- A co-design architecture on sparse attention☆44Updated 3 years ago
- ☆20Updated this week
- An efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences☆20Updated 8 months ago
- ☆79Updated 11 months ago
- The codes and artifacts associated with our MICRO'22 paper titled: "Adaptable Butterfly Accelerator for Attention-based NNs via Hardware …☆110Updated last year
- SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration (Full Paper Accepted in FPGA'24)☆26Updated 3 months ago
- ☆24Updated 7 months ago
- Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)☆12Updated 4 months ago
- Open-source Framework for HPCA2024 paper: Gemini: Mapping and Architecture Co-exploration for Large-scale DNN Chiplet Accelerators☆52Updated 2 months ago
- ViTALiTy (HPCA'23) Code Repository☆19Updated last year
- MICRO22 artifact evaluation for Sparseloop☆38Updated 2 years ago
- FPGA-based hardware accelerator for Vision Transformer (ViT), with Hybrid-Grained Pipeline.☆9Updated 2 months ago
- ☆30Updated 4 years ago
- ☆81Updated 4 months ago
- A framework for fast exploration of the depth-first scheduling space for DNN accelerators☆31Updated last year
- ☆45Updated 2 months ago
- Multi-core HW accelerator mapping optimization framework for layer-fused ML workloads.☆38Updated this week
- An FPGA Accelerator for Transformer Inference☆72Updated 2 years ago
- Open-source of MSD framework☆14Updated last year
- The framework for the paper "Inter-layer Scheduling Space Definition and Exploration for Tiled Accelerators" in ISCA 2023.☆46Updated 2 weeks ago
- ☆34Updated last year
- Linux docker for the DNN accelerator exploration infrastructure composed of Accelergy and Timeloop☆45Updated this week
- Torch2Chip (MLSys, 2024)☆50Updated 2 months ago
- A Spatial Accelerator Generation Framework for Tensor Algebra.☆52Updated 2 years ago
- ☆45Updated 8 months ago
- RTL implementation of Flex-DPE.☆89Updated 4 years ago
- Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts☆84Updated 6 months ago