microsoft / nnscaler
nnScaler: Compiling DNN models for Parallel Training
☆101Updated last month
Alternatives and similar repositories for nnscaler:
Users that are interested in nnscaler are comparing it to the libraries listed below
- ☆72Updated 3 years ago
- ☆88Updated 4 months ago
- ☆137Updated 8 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆153Updated 5 months ago
- High performance Transformer implementation in C++.☆109Updated 2 months ago
- ☆75Updated 2 years ago
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆60Updated this week
- ☆79Updated 3 months ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆78Updated 4 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆82Updated last year
- ☆53Updated 9 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆51Updated 7 months ago
- LLM serving cluster simulator☆93Updated 10 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆201Updated last year
- ☆80Updated 2 years ago
- A baseline repository of Auto-Parallelism in Training Neural Networks☆143Updated 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…☆233Updated 2 weeks ago
- An experimental parallel training platform☆54Updated 11 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆317Updated this week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 9 months ago
- ☆87Updated 6 months ago
- A resilient distributed training framework☆89Updated 11 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆112Updated last year
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆150Updated 8 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆147Updated this week
- Curated collection of papers in MoE model inference☆106Updated last month
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆149Updated 6 months ago
- A low-latency & high-throughput serving engine for LLMs☆325Updated last month
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆22Updated 10 months ago
- Stateful LLM Serving☆48Updated last week