b10448 b10447
ggml-org/llama.cppAug 15, 2026 → Aug 15, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10448 and b10447. This page updates automatically — usually within a minute.
The Two Releases
b10448
b10448
Aug 15, 2026· 2 months ago
Major feature release adding support for the Kimi-K3 text model, which introduces novel architectural features like latent MoE, situ activation, and MLA output gates. It also includes a dedicated chat format for K3 and MXFP4 quantization support.
Full release notesb10447
b10447
Aug 15, 2026· 2 months ago
This release redesigns the server's yield-to-queue thread model by moving speculative processing into the worker thread and swapping the worker/main thread design for improved concurrency.
Full release notes