kooyunmo / cuda-uvm-gpt2
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
- ☆23Updated 2 years ago
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆13Updated 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…☆28Updated last year
- ☆25Updated 4 years ago
- ☆35Updated last year
- GVProf: A Value Profiler for GPU-based Clusters☆49Updated 10 months ago
- ☆31Updated 8 months ago
- ☆48Updated last month
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆40Updated 2 years ago
- ☆33Updated 2 years ago
- ☆74Updated 2 years ago
- ☆16Updated 2 years ago
- ☆17Updated 3 years ago
- ☆37Updated 3 years ago
- ☆44Updated last month
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆50Updated 8 months ago
- ☆47Updated 5 years ago
- Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access (ACM EuroSys '23)☆55Updated 10 months ago
- ☆67Updated 4 years ago
- Efficient-Tensor-Management-on-HM-for-Deep-Learning☆9Updated 3 years ago
- ☆14Updated 4 years ago
- ☆30Updated 11 months ago
- Thinking is hard - automate it☆19Updated 2 years ago
- ☆35Updated 4 years ago
- A pattern-based algorithmic autotuner for graph processing on GPUs.☆30Updated 2 months ago
- Implementation of vDNN++; an improvement over vDNN☆17Updated 6 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆53Updated 9 months ago
- ☆24Updated last year
- Artifact for OSDI'23: MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Mult…☆38Updated 10 months ago
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆83Updated last month