Pinned Loading

1. auto-tuning-vllm auto-tuning-vllm Public

   Auto-tuning for vllm. Getting the best performance out of your LLM deployment (vllm+guidellm+optuna)

   Python 64 18

2. performance-dashboard performance-dashboard Public

   A comprehensive performance analysis dashboard for RHAIIS (Red Hat AI Inference server) benchmarks. This dashboard provides interactive visualizations and analysis of AI model performance across di…

   Python 6 7

3. LLM-inference-benchmark-guide LLM-inference-benchmark-guide Public

   This repository serves as a comprehensive methodology guide for benchmarking LLM inference across a variety of hardware accelerators and inference engines.

   4

4. llm-d-bench llm-d-bench Public

   llm-d benchmarking automation work

   Python 3

5. forge forge Public

   Framework for Orchestrating Runtime Gen-AI Experiments

   Python 3 9

6. fournos fournos Public

   Fournos is a Kubernetes operator that schedules benchmark jobs via Kueue and executes them as Tekton PipelineRuns on remote clusters through the FORGE framework.

   Python 3 7