DicardoX / Research-Space
This repository is established to store personal notes and annotated papers during daily research.
☆86Updated this week
Related projects ⓘ
Alternatives and complementary repositories for Research-Space
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆166Updated this week
- ☆55Updated 2 years ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆75Updated 3 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆126Updated 3 weeks ago
- paper and its code for AI System☆210Updated 2 months ago
- Curated collection of papers in machine learning systems☆156Updated last month
- LLM serving cluster simulator☆74Updated 6 months ago
- ☆42Updated last month
- High performance Transformer implementation in C++.☆78Updated last month
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆79Updated last year
- ☆82Updated 5 months ago
- ☆251Updated 9 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 6 months ago
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆45Updated last month
- Compiler for Dynamic Neural Networks☆43Updated 11 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆46Updated 3 months ago
- Summary of some awesome work for optimizing LLM inference☆34Updated this week
- An interference-aware scheduler for fine-grained GPU sharing☆108Updated 5 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆85Updated last year
- A baseline repository of Auto-Parallelism in Training Neural Networks☆142Updated 2 years ago
- ☆12Updated 6 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆56Updated 5 months ago
- ☆37Updated 3 years ago
- ☆14Updated 5 months ago
- nnScaler: Compiling DNN models for Parallel Training☆62Updated 2 weeks ago
- ☆23Updated last year
- ☆12Updated 7 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated 2 months ago
- ☆51Updated last month
- Galvatron is an automatic distributed training system designed for Transformer models, including Large Language Models (LLMs).☆36Updated this week