eis-lab / sage
Experimental deep learning framework written in Rust
☆13Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for sage
- MobiSys#114☆21Updated last year
- Source code for the paper: "A Latency-Predictable Multi-Dimensional Optimization Framework forDNN-driven Autonomous Systems"☆19Updated 3 years ago
- ☆22Updated last year
- SOTA Learning-augmented Systems☆32Updated 2 years ago
- Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access (ACM EuroSys '23)☆53Updated 7 months ago
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆55Updated 2 weeks ago
- Multi-Instance-GPU profiling tool☆53Updated last year
- zTT: Learning-based DVFS with Zero Thermal Throttling for Mobile Devices [MobiSys'21] - Artifact Evaluation☆20Updated 3 years ago
- ☆38Updated 7 months ago
- Official PyTorch Implementation of HELP: Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning (NeurIPS 2021 Spotlight…☆60Updated 3 months ago
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆33Updated last year
- The open-source project for "Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading"[MobiCom'2022]☆18Updated 2 years ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆34Updated 2 years ago
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆80Updated 2 months ago
- [DATE 2023] Pipe-BD: Pipelined Parallel Blockwise Distillation☆11Updated last year
- This is a list of awesome edgeAI inference related papers.☆88Updated 10 months ago
- Study Group of Deep Learning Compiler☆152Updated last year
- one-shot-tuner☆8Updated last year
- ☆21Updated 3 months ago
- ☆20Updated last month
- A version of XRBench-MAESTRO used for MLSys 2023 publication☆22Updated last year
- [HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System☆34Updated 8 months ago
- PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models. ICML 2021☆54Updated 3 years ago
- ☆18Updated 2 years ago
- ☆14Updated 2 years ago
- ☆101Updated last year
- PyTorch compilation tutorial covering TorchScript, torch.fx, and Slapo☆19Updated last year
- 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
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆8Updated 8 months ago
- ☆130Updated 3 months ago