v0.30.0-rc32: llama-server followups (#16353)
🔒
https://github.com
«llama-server followups
Misc fixes for #16031
Add back dropped ROCm build flag for multi-GPU support on windows
Fix amdhip64_*.dll version detection for "latest" selection
Fix embeddings API for consistent normalize beh...»
Automatische Weiterleitung...
1.5s