liu445126256 / FuncPipe
☆10Updated last year
Related projects: ⓘ
- ☆21Updated last year
- ☆19Updated last year
- A benchmark suite for evaluating FaaS scheduler.☆22Updated last year
- ☆67Updated last year
- Model-less Inference Serving☆78Updated 10 months ago
- Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)☆11Updated 3 months ago
- A Generic Resource-Aware Hyperparameter Tuning Execution Engine☆15Updated 2 years ago
- ☆13Updated 2 years ago
- Machine learning on serverless platform☆7Updated 2 years ago
- ☆39Updated last year
- Serverless for all computation☆41Updated last year
- ☆19Updated 2 years ago
- ☆41Updated 3 years ago
- The source code of INFless，a native serverless platform for AI inference.☆33Updated last year
- MemLiner is a remote-memory-friendly runtime system.☆30Updated last year
- Vector search with bounded performance.☆33Updated 7 months ago
- An Attention Superoptimizer☆19Updated 4 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated 4 months ago
- ☆23Updated 2 months ago
- ☆14Updated last year
- Cupcake: A Compression Scheduler for Scalable Communication-Efficient Distributed Training (MLSys '23)☆8Updated last year
- ☆14Updated 2 years ago
- ☆14Updated 3 years ago
- Dorylus: Affordable, Scalable, and Accurate GNN Training☆77Updated 3 years ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆39Updated 2 years ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆46Updated 3 weeks ago
- Ok-Topk is a scheme for distributed training with sparse gradients. Ok-Topk integrates a novel sparse allreduce algorithm (less than 6k c…☆23Updated last year
- Molecule's artifact for ASPLOS'22☆29Updated 2 years ago
- Artifacts for our SIGCOMM'22 paper Muri☆38Updated 8 months ago
- SOTA Learning-augmented Systems☆32Updated 2 years ago