Skip to content

Refactor core GGUF loading to use a shared backend-aware reader policy across Qwen and LFM2 models#70

Merged
zinyando merged 5 commits intomainfrom
centralized-model-io
Mar 5, 2026
Merged

Refactor core GGUF loading to use a shared backend-aware reader policy across Qwen and LFM2 models#70
zinyando merged 5 commits intomainfrom
centralized-model-io

Conversation

@zinyando
Copy link
Copy Markdown
Contributor

@zinyando zinyando commented Mar 5, 2026

Add centralized GGUF mmap/reader primitives, route Qwen3/Qwen3.5/LFM2 text loaders, Qwen3.5 mmproj loading, and shared GGUF utilities through them, unify device-to-backend mapping, and remove the unused mmproj_inspect binary.

@zinyando zinyando merged commit 13b39d6 into main Mar 5, 2026
@zinyando zinyando deleted the centralized-model-io branch March 12, 2026 09:41
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant