Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
Repository Index
96,838 visible repositories in the index
1–9 of 9 · Most stars
Easy benchmarking of all publicly accessible implementations of convnets
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
Macrobenchmarking framework for Elasticsearch
PerfKit Benchmarker (PKB) contains a set of benchmarks to measure and compare cloud offerings. The benchmarks use default settings to reflect what most users will see. PerfKit Benchmarker is licensed under the Apache 2 license terms. Please make sure to read, understand and agree to the terms of the LICENSE and CONTRIBUTING files before proceeding.
A Fair and Scalable Time Series Forecasting Benchmark and Toolkit.
- time-series
- traffic-forecasting
- benchmarking
- long-time-series-forecasting
:bar_chart: Benchmark multiple object trackers (MOT) in Python
- object-tracking
- object-detection
- clear-mot-metrics
- benchmark
A comparison between some VPS providers. It uses Ansible to perform a series of automated benchmark tests over the VPS servers that you specify. It allows the reproducibility of those tests by anyone that wanted to compare these results to their own. All the tests results are available in order to provide independence and transparency.
- vps
- ansible
- comparison
- python
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
- cifar10
- deep-learning
- experimentation
- machine-learning