Open source

ggml-org/llama.cpp b10361

GitHub Releases · github-actions[bot] · 1 month ago

<details open> model : fix SWA not being enabled for EXAONE 4.5 (#26848) * model : fix SWA not being enabled for EXAONE 4.5 load_arch_hparams tests `hparams.n_layer() == 64` before LLM_KV_NEXTN_PREDICT_LAYERS has been read. n_layer() returns n_layer_all - n_layer_nextn and n_lay…

Open on github.com ↗

Source and ranking details

Source adapter: github-releases
Source weight: 3
Points: 0
Age: 905.7 h
Stored score: 0.00001
Current score: 0.00001
First seen: 2026-08-12T05:24:31.913Z

Newsletter

Get practical AI engineering notes

Receive source-checked analysis of models, agents, evaluation, retrieval, and production reliability. Sent only when there is useful work to share.