b10412 b10411
ggml-org/llama.cppAug 13, 2026 → Aug 13, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10412 and b10411. This page updates automatically — usually within a minute.
The Two Releases
b10412
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 notesb10411
b10411
Aug 13, 2026· 2 months ago
Optimizes the Flash-Attention implementation by vectorizing the V-cache F16 to F32 conversion process.
Full release notes