UbiquitousLearning / Mandheling-DSP-Training
The open-source project for "Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading"[MobiCom'2022]
☆18Updated 2 years ago
Related projects: ⓘ
- Compiler for Dynamic Neural Networks☆42Updated 10 months ago
- ☆93Updated 8 months ago
- MobiSys#114☆21Updated last year
- DietCode Code Release☆59Updated 2 years ago
- ☆40Updated 4 months ago
- This is a list of awesome edgeAI inference related papers.☆84Updated 8 months ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆35Updated 3 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆110Updated last month
- ☆19Updated 2 months ago
- ☆127Updated last month
- Canvas: End-to-End Kernel Architecture Search in Neural Networks☆13Updated 10 months ago
- PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections☆112Updated 2 years ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆79Updated last year
- ☆74Updated last year
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆153Updated this week
- Automatic Mapping Generation, Verification, and Exploration for ISA-based Spatial Accelerators☆100Updated last year
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆31Updated last year
- ☆20Updated last year
- ☆39Updated last year
- Source code for the paper: "A Latency-Predictable Multi-Dimensional Optimization Framework forDNN-driven Autonomous Systems"☆19Updated 3 years ago
- ☆86Updated last year
- ☆72Updated last year
- ☆75Updated 10 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆46Updated 3 weeks ago
- Summary of some awesome work for optimizing LLM inference☆26Updated this week
- ☆30Updated 2 years ago
- Ok-Topk is a scheme for distributed training with sparse gradients. Ok-Topk integrates a novel sparse allreduce algorithm (less than 6k c…☆23Updated last year
- LLM serving cluster simulator☆55Updated 4 months ago
- An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.☆49Updated last month
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆55Updated 4 months ago