Skip to content

llm-d-workload-variant-autoscaler nightly-0a926fab Public Latest

Workload Variant Autoscaler (WVA) - GPU-aware autoscaler for LLM inference workloads

Install from the command line
Learn more about packages
$ docker pull ghcr.io/llm-d/llm-d-workload-variant-autoscaler:nightly-0a926fab

Recent tagged image versions

  • nightly-0a926fab
    Published about 2 hours ago · Digest
    sha256:9999ba7539f1e8faeadd2236f2ddbd7735db0c4d3bc5d7c9a5157e764196c43f
    0 Version downloads
  • nightly-2976e4ee
    Published 22 days ago · Digest
    sha256:06b835e47256f6178544729b459ded8f2cf66dcf4599491b58bb8cc46ad35708
    1 Version downloads
  • main
    Published 24 days ago · Digest
    sha256:dbeb3e6bec40c8f789475e473d9b665e066e6c1485bd7bda5a3ffe9c0e5b3c8e
    2 Version downloads
  • nightly-bebbe88f
    Published 28 days ago · Digest
    sha256:897bf45eb84f44d3afe20d871cfa4d644fea2a38588c0547e8a73dff8c003130
    0 Version downloads
  • latest v0.9.0
    Published 29 days ago · Digest
    sha256:121ce4a1a0c5e6a035000e2826922eb9db9047236ed943777393f8215568307c
    6,540 Version downloads
View all tagged versions

Loading

Details

Last published

2 hours ago

Discussions

1

Issues

152

Total downloads

790K