github gpustack/runner v0.1.31.post4

4 hours ago

Features

  • feat: upgrade cuda/sglang, cuda/vllm, rocm/sglang, rocm/vllm — vLLM 0.32.0 and SGLang 0.5.22 (#382)

Fixes

  • ci(auto_sync): authenticate upstream queries, name rate limits (#383)

Other

  • chore: catalog refresh — vLLM 0.32.0 and SGLang 0.5.22 published on CUDA 13.0/12.9 and ROCm 7.2 images (#384, #385, #386, #387)
  • docs: record vLLM 0.32.0 and SGLang 0.5.22 support (#388)

Full Changelog: v0.1.31.post3...v0.1.31.post4

Don't miss a new runner release

NewReleases is sending notifications on new releases.