b10520 b10519
ggml-org/llama.cppAug 20, 2026 → Aug 20, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10520 and b10519. This page updates automatically — usually within a minute.
The Two Releases
b10520
b10520
Aug 20, 2026· 2 months ago
Fixes a compilation issue on 32-bit ARM architectures by gating the use of `__fp16` on the IEEE half format, ensuring compatibility with toolchains that provide the type but use a different format.
Full release notesb10519
b10519
Aug 20, 2026· 2 months ago
Refactors the server's sleep handling logic to allow access to the `/metrics` endpoint even when the server is in a sleeping state, improving observability and fixing race conditions.
Full release notes