Skip to content

v0.2.0

Choose a tag to compare

@codyw912 codyw912 released this 29 Jan 20:09
· 31 commits to main since this release
v0.2.0
52ee0e8
  • Add NVIDIA NeMo backend scaffold, smoke script, and docs for CUDA setup.
  • Add model eviction controls, admin unload/status endpoints, and CUDA graph disable toggle.