mental2008 / awesome-papers
Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and other interesting stuffs).
☆65Updated this week
Alternatives and similar repositories for awesome-papers:
Users that are interested in awesome-papers are comparing it to the libraries listed below
- An interference-aware scheduler for fine-grained GPU sharing☆121Updated this week
- LLM serving cluster simulator☆90Updated 9 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 7 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆80Updated last year
- Artifacts for our NSDI'23 paper TGS☆71Updated 7 months ago
- ☆62Updated 2 years ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆109Updated 11 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆142Updated 3 months ago
- This repository is established to store personal notes and annotated papers during daily research.☆106Updated 3 weeks ago
- ☆37Updated 3 years ago
- Curated collection of papers in machine learning systems☆222Updated last month
- Artifacts for our ASPLOS'23 paper ElasticFlow☆53Updated 8 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆90Updated 2 years ago
- ☆44Updated last month
- High performance Transformer implementation in C++.☆99Updated last week
- ☆82Updated 2 months ago
- A resilient distributed training framework☆88Updated 9 months ago
- Stateful LLM Serving☆44Updated 6 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆59Updated 8 months ago
- Synthesizer for optimal collective communication algorithms☆102Updated 9 months ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆127Updated 2 years ago
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆68Updated last year
- ☆16Updated 8 months ago
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆51Updated last year
- ☆23Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated 5 months ago
- Curated collection of papers in MoE model inference☆41Updated last week
- ☆273Updated last year
- Microsoft Collective Communication Library☆61Updated 2 months ago
- [ATC '24] Metis: Fast automatic distributed training on heterogeneous GPUs (https://www.usenix.org/conference/atc24/presentation/um)☆24Updated 2 months ago