LAB LEDGER DESK
00:00:00 UTC2026-11-17
Official sources only·Nothing invented

Ollama · Launch ·

v0.40.2-rc0: server: hide duplicate and downgrade guards from list (#18874)

When a legacy GGUF which requires our llama.cpp patch set is loaded, we do a lazy conversion on disk to make it llama.cpp compatible. …

What moved

When a legacy GGUF which requires our llama.cpp patch set is loaded, we do a lazy conversion on disk to make it llama.cpp compatible. To support downgrades, we temporarily hold both the new and old GGUFs and create a shadow v1 manifest tag to prevent the downgraded server from deleting the new blobs. …

Why it matters

Filed as a launch filing from Ollama, 2026-10-08. The desk tags this brief LLM.

On the record

  • Filed from the Ollama official GitHub releases feed on 2026-10-08.
  • Primary source host: github.com.
  • When a legacy GGUF which requires our llama.cpp patch set is loaded, we do a lazy conversion on disk to make it llama.cpp compatible.
Primary source
github.com
Desk
Logged as brief 088
Cite this briefv0.40.2-rc0: server: hide duplicate and downgrade guards from list (#18874) (Ollama, 2026-10-08) — https://labledgerdesk.pages.dev/b/2026/10/08/v0-40-2-rc0-server-hide-duplicate-and-downgrade-guards-from-list-18874/