kooyunmo / cuda-uvm-gpt2Links
PyTorch-UVM on super-large language models.
☆15Updated 4 years ago
Alternatives and similar repositories for cuda-uvm-gpt2
Users that are interested in cuda-uvm-gpt2 are comparing it to the libraries listed below
Sorting:
- ☆23Updated 2 years ago
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆14Updated 4 years ago
- ☆36Updated last year
- ☆26Updated 4 years ago
- This serves as a repository for reproducibility of the SC21 paper "In-Depth Analyses of Unified Virtual Memory System for GPU Accelerated…☆31Updated last year
- GVProf: A Value Profiler for GPU-based Clusters☆49Updated last year
- ☆79Updated 2 years ago
- ☆34Updated 11 months ago
- ☆22Updated 2 years ago
- ☆37Updated 3 years ago
- ☆51Updated 5 years ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- ☆53Updated 4 years ago
- ☆18Updated 4 years ago
- ☆30Updated last year
- ☆49Updated 5 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆94Updated 2 years ago
- Thinking is hard - automate it☆19Updated 2 years ago
- A benchmarking suite for heterogeneous systems. The primary goal of this project is to improve and update aspects of existing benchmarkin…☆42Updated last year
- [ACM EuroSys '23] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆56Updated last year
- ☆16Updated 2 years ago
- ☆36Updated last month
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆51Updated last year
- ☆74Updated 4 years ago
- ☆24Updated last year
- Sharing the codebase and steps for artifact evaluation/reproduction for MICRO 2024 paper☆9Updated 9 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated last year
- LLM serving cluster simulator☆100Updated last year
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆25Updated 3 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 9 months ago