eniac / paellaLinks
Paella: Low-latency Model Serving with Virtualized GPU Scheduling
☆58Updated last year
Alternatives and similar repositories for paella
Users that are interested in paella are comparing it to the libraries listed below
Sorting:
- ☆79Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated 11 months ago
- ☆49Updated 5 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 9 months ago
- ☆22Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆80Updated 2 weeks ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆94Updated 2 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated last year
- NCCL Profiling Kit☆134Updated 11 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- ☆65Updated last month
- ☆37Updated 3 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆137Updated 4 months ago
- Artifact from "Hardware Compute Partitioning on NVIDIA GPUs". THIS IS A FORK OF BAKITAS REPO☆27Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆171Updated 7 months ago
- Synthesizer for optimal collective communication algorithms☆106Updated last year
- Microsoft Collective Communication Library☆65Updated 6 months ago
- ☆36Updated 4 months ago
- Ultra | Ultimate | Unified CCL☆75Updated last week
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆19Updated last month
- ☆23Updated 2 years ago
- PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections☆121Updated 2 years ago
- High performance Transformer implementation in C++.☆123Updated 4 months ago
- An experimental parallel training platform☆54Updated last year
- ☆62Updated 11 months ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆12Updated last year
- SOTA Learning-augmented Systems☆36Updated 3 years ago
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆25Updated 3 months ago