Shenggan / awesome-distributed-ml
A curated list of awesome projects and papers for distributed training or inference
☆198Updated last month
Related projects ⓘ
Alternatives and complementary repositories for awesome-distributed-ml
- A baseline repository of Auto-Parallelism in Training Neural Networks☆141Updated 2 years ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆175Updated this week
- paper and its code for AI System☆216Updated 2 months ago
- A low-latency & high-throughput serving engine for LLMs☆247Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆240Updated last week
- Curated collection of papers in machine learning systems☆167Updated last month
- nnScaler: Compiling DNN models for Parallel Training☆77Updated 3 weeks ago
- A large-scale simulation framework for LLM inference☆278Updated this week
- A fast communication-overlapping library for tensor parallelism on GPUs.☆226Updated 3 weeks ago
- ☆502Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆181Updated last year
- Latency and Memory Analysis of Transformer Models for Training and Inference☆356Updated last week
- Zero Bubble Pipeline Parallelism☆283Updated last week
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆135Updated last month
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆79Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆364Updated 3 months ago
- A resilient distributed training framework☆85Updated 7 months ago
- A high-performance distributed deep learning system targeting large-scale and automated distributed training. If you have any interests, …☆104Updated 11 months ago
- ☆289Updated 7 months ago
- Efficient and easy multi-instance LLM serving☆219Updated this week
- ☆70Updated 2 years ago
- ☆169Updated 4 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆250Updated this week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆103Updated 3 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆451Updated 2 weeks ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆75Updated this week
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆46Updated 3 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆278Updated 4 months ago
- ☆56Updated last week
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆102Updated 9 months ago