Skip to content

Open source / #17103

Open source

ggml-org/llama.cpp b10690

GitHub Releases · github-actions[bot] · 19 days ago

<details open> memory : copy Hadamard matrix to k_rot tensor only if it has buffer assigned to prevent crashes during context shift of unquantized K cache (#27967) Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> Co-authored-by: AesSedai <7980540+AesSedai@users.noreply.gi…

Source adapter
github-releases
Source weight
3
Points
0
Age
459.2 h
Stored score
0.00003
Current score
0.00003
First seen
2026-08-30T08:37:05.893Z

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.