casys-kaist / EnvPipe
☆24Updated last year
Alternatives and similar repositories for EnvPipe:
Users that are interested in EnvPipe are comparing it to the libraries listed below
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆10Updated last year
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated 2 years ago
- ☆53Updated 4 years ago
- [ACM EuroSys '23] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆56Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated 11 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆24Updated 5 months ago
- ☆23Updated 2 years ago
- SOTA Learning-augmented Systems☆36Updated 2 years ago
- LLM serving cluster simulator☆96Updated 11 months ago
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆109Updated last month
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 8 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆17Updated last year
- ☆14Updated 3 years ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆19Updated last year
- Multi-Instance-GPU profiling tool☆57Updated 2 years ago
- ☆47Updated 3 months ago
- ☆16Updated 2 years ago
- ☆59Updated 10 months ago
- LLM Inference analyzer for different hardware platforms☆62Updated 2 weeks ago
- ☆14Updated 3 years ago
- ☆49Updated 2 years ago
- ☆23Updated 9 months ago
- ☆16Updated last year
- ☆37Updated 3 years ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆24Updated 11 months ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆25Updated 2 months ago
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆23Updated 4 months ago
- ☆66Updated 3 weeks ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆49Updated 2 years ago