b10413 b10412
ggml-org/llama.cppAug 13, 2026 → Aug 13, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10413 and b10412. This page updates automatically — usually within a minute.
The Two Releases
b10413
b10413
Aug 13, 2026· 2 months ago
Adds automatic detection of speculative decoding types (dspark and dflash) when loading local draft models from GGUF metadata.
Full release notesb10412
b10412
Aug 13, 2026· 2 months ago
Enables backend sampling support for speculative decoding, allowing it to work with both dflash and dspark models.
Full release notes