UofT-EcoSystem / Tempo
Memory footprint reduction for transformer models
☆11Updated last year
Related projects: ⓘ
- ☆39Updated last year
- ☆62Updated 3 years ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆33Updated last year
- 16-fold memory access reduction with nearly no loss☆35Updated last month
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆25Updated 6 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆70Updated last year
- ☆33Updated 3 weeks ago
- ☆65Updated 2 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆110Updated last month
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆14Updated 4 months ago
- pytorch-profiler☆47Updated last year
- ☆127Updated last month
- Python package for rematerialization-aware gradient checkpointing☆22Updated 10 months ago
- The documents for TVM Unity☆11Updated last month
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆70Updated last month
- ☆30Updated 3 months ago
- Boost hardware utilization for ML training workloads via Inter-model Horizontal Fusion☆32Updated 4 months ago
- ☆7Updated last year
- ☆83Updated 3 weeks ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆13Updated 9 months ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆19Updated 6 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆41Updated 3 weeks ago
- FTPipe and related pipeline model parallelism research.☆41Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆90Updated last month
- PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections☆112Updated 2 years ago
- A high-performance distributed deep learning system targeting large-scale and automated distributed training. If you have any interests, …☆101Updated 9 months ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆35Updated 3 months ago
- ☆15Updated this week
- ☆20Updated last year
- [IJCAI2023] An automated parallel training system that combines the advantages from both data and model parallelism. If you have any inte…☆51Updated last year