IBM / LLM-performance-predictionLinks
Predict the performance of LLM inference services
☆20Updated last month
Alternatives and similar repositories for LLM-performance-prediction
Users that are interested in LLM-performance-prediction are comparing it to the libraries listed below
Sorting:
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆130Updated last year
- ☆43Updated last year
- Stateful LLM Serving☆87Updated 7 months ago
- ☆27Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆150Updated 9 months ago
- LLM Serving Performance Evaluation Harness☆79Updated 8 months ago
- ☆136Updated last year
- Artifacts for our NSDI'23 paper TGS☆89Updated last year
- ☆74Updated 2 weeks ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆215Updated 3 months ago
- A resilient distributed training framework☆96Updated last year
- ☆63Updated last month
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆47Updated last year
- ☆35Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆68Updated 2 weeks ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated 11 months ago
- The source code of INFless，a native serverless platform for AI inference.☆41Updated 3 years ago
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆56Updated 2 years ago
- ☆312Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆188Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆13Updated last year
- ☆21Updated last year
- HeliosArtifact☆21Updated 3 years ago
- A Deep Learning Cluster Scheduler☆39Updated 4 years ago
- ☆24Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆53Updated 2 years ago
- A framework for generating realistic LLM serving workloads☆73Updated 3 weeks ago
- ☆23Updated 3 years ago
- ☆38Updated 4 months ago