Nerif-AI / Nerif
LLM-powered Python
☆14Updated last month
Alternatives and similar repositories for Nerif:
Users that are interested in Nerif are comparing it to the libraries listed below
- Easy-GPT4O opensource version☆73Updated 9 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆143Updated 4 months ago
- ☆15Updated 2 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- High-speed and easy-use LLM serving framework for local deployment☆87Updated last week
- ☆87Updated 4 months ago
- Fast OS-level support for GPU checkpoint and restore☆153Updated last month
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 8 months ago
- Stateful LLM Serving☆46Updated 6 months ago
- A large-scale simulation framework for LLM inference☆323Updated 3 months ago
- High performance Transformer implementation in C++.☆101Updated last month
- ☆83Updated 3 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated 5 months ago
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆70Updated 3 weeks ago
- ☆43Updated 7 months ago
- ☆23Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆133Updated this week
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆145Updated 4 months ago
- Bamboo-7B Large Language Model☆89Updated 10 months ago
- ☆50Updated 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
- Microsoft Collective Communication Library☆61Updated 2 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆112Updated 11 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆17Updated this week
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆17Updated last year
- Compiler for Dynamic Neural Networks☆45Updated last year
- VQPy: An object-oriented approach to modern video analytics☆37Updated 3 months ago
- nnScaler: Compiling DNN models for Parallel Training☆91Updated this week
- LLM checkpointing for DeepSpeed/Megatron☆13Updated last week
- Thunder Research Group's Collective Communication Library☆33Updated 9 months ago