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
- ☆36Updated last year
- ☆25Updated 4 years ago
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆14Updated 4 years ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 2 years ago
- GVProf: A Value Profiler for GPU-based Clusters☆49Updated 11 months ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆49Updated 9 months ago
- ☆31Updated 9 months ago
- This serves as a repository for reproducibility of the SC21 paper "In-Depth Analyses of Unified Virtual Memory System for GPU Accelerated…☆29Updated last year
- ☆75Updated 2 years ago
- ☆24Updated last year
- ☆46Updated 2 months ago
- ☆37Updated 3 years ago
- Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access (ACM EuroSys '23)☆56Updated 11 months ago
- LLM Inference analyzer for different hardware platforms☆54Updated this week
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 10 months ago
- ☆21Updated 6 years ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆92Updated 2 years ago
- ☆53Updated 4 years ago
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆93Updated 2 weeks ago
- ☆35Updated 4 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆10Updated last year
- ☆19Updated last month
- LLM serving cluster simulator☆93Updated 10 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated 6 months ago
- ☆68Updated 4 years ago
- Efficient-Tensor-Management-on-HM-for-Deep-Learning☆9Updated 3 years ago
- A Cycle-level simulator for M2NDP☆24Updated 3 months ago
- Exploring the Design Space of Page Management for Multi-Tiered Memory Systems (USENIX ATC '21)☆45Updated 2 years ago
- A benchmarking suite for heterogeneous systems. The primary goal of this project is to improve and update aspects of existing benchmarkin…☆40Updated last year