b10414 b10413
ggml-org/llama.cppAug 13, 2026 → Aug 13, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10414 and b10413. This page updates automatically — usually within a minute.
The Two Releases
b10414
b10414
Aug 13, 2026· 2 months ago
Adds support for the TQ2_0 (ternary 2-bit) quantization type to the Metal backend and optimizes the mul_mv kernel.
Full release notesb10413
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 notes