dywsjtu / apparate
Code for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
☆16Updated this week
Related projects ⓘ
Alternatives and complementary repositories for apparate
- An Attention Superoptimizer☆20Updated 6 months ago
- Stateful LLM Serving☆38Updated 3 months ago
- Vector search with bounded performance.☆33Updated 9 months ago
- Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)☆11Updated 5 months ago
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated last year
- SOTA Learning-augmented Systems☆33Updated 2 years ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆19Updated 9 months ago
- ☆24Updated last year
- General system research material (not limited to paper) reading notes.☆20Updated 3 years ago
- website for systems seminar at UIUC☆17Updated this week
- Reading seminar in Harvard Cloud Networking and Systems Group☆16Updated 2 years ago
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆17Updated 2 years ago
- ☆13Updated 2 years ago
- 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
- ☆51Updated 3 years ago
- Cupcake: A Compression Scheduler for Scalable Communication-Efficient Distributed Training (MLSys '23)☆9Updated last year
- ☆14Updated 2 years ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated 3 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆47Updated last year
- ☆46Updated 5 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 6 months ago
- ☆17Updated 5 months ago
- Arya: Arbitrary Graph Pattern Mining with Decomposition-based Sampling☆13Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆102Updated 9 months ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆39Updated 2 years ago
- ☆26Updated 2 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆57Updated 5 months ago
- Primo: Practical Learning-Augmented Systems with Interpretable Models☆18Updated 10 months ago
- Code for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆38Updated 2 years ago