WukLab / InferCept
☆17Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for InferCept
- ☆46Updated 5 months ago
- Stateful LLM Serving☆38Updated 3 months ago
- ☆15Updated 4 months ago
- ☆55Updated last week
- ☆24Updated 2 weeks ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆74Updated last year
- Python package for rematerialization-aware gradient checkpointing☆23Updated last year
- ☆14Updated 5 months ago
- ☆51Updated last month
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny model can tell you the verbosity of an LLM (…☆22Updated 5 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆47Updated last year
- A resilient distributed training framework☆85Updated 7 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆133Updated last month
- FGNN's artifact evaluation (EuroSys 2022)☆17Updated 2 years ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆14Updated 11 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆11Updated 5 months ago
- ☆23Updated last year
- Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)☆11Updated 5 months ago
- ☆67Updated last month
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated last year
- An Attention Superoptimizer☆20Updated 6 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆17Updated last week
- Artifact for OSDI'23: MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Mult…☆37Updated 8 months ago
- ☆13Updated 2 years ago
- Compiler for Dynamic Neural Networks☆43Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆101Updated 9 months ago
- Surrogate-based Hyperparameter Tuning System☆27Updated last year
- Code for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆16Updated last month
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆57Updated 5 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆78Updated last year