WukLab / preble
Stateful LLM Serving
☆25Updated last month
Related projects: ⓘ
- ☆30Updated 3 months ago
- ☆30Updated this week
- ☆47Updated 3 weeks ago
- ☆19Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆92Updated 6 months ago
- ☆15Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆89Updated last week
- An Attention Superoptimizer☆19Updated 4 months ago
- SOTA Learning-augmented Systems☆32Updated 2 years ago
- Vector search with bounded performance.☆33Updated 7 months ago
- ☆12Updated 2 months ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆35Updated 3 months ago
- ☆15Updated 2 months ago
- ☆35Updated 2 months ago
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆17Updated 2 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆110Updated last month
- ☆14Updated last year
- LLM serving cluster simulator☆55Updated 4 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆13Updated 9 months ago
- A resilient distributed training framework☆78Updated 5 months ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆33Updated last year
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆19Updated 6 months ago
- Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training☆18Updated 6 months ago
- Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)☆11Updated 3 months ago
- ☆32Updated this week
- Thunder Research Group's Collective Communication Library☆20Updated 4 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆14Updated 4 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆46Updated 3 weeks ago
- ☆48Updated 3 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆54Updated 3 months ago