Jesse Gross c2f5d6662b ollamarunner: Re-enable worst case graph preallocation. ... Worst case graph preallocation was disabled by a27462b "ollamarunner: Temporarily disable worst case graph preallocation" since it caused crashes with large batches when not using the GPU. This backports upstream llama.cpp commit f057808 "ggml: Don't assert fail when tensor data changes (#13222)", which fixes the underlying bug and allows reverting the previous workaround.		2025-05-02 12:22:47 -07:00
..
cmake	ml: add missing cmake property and remove additional CMakeLists.txt (#10310)	2025-04-16 18:56:29 -07:00
include	llama: update to commit e1e8e099 (#10513)	2025-05-01 18:24:09 -07:00
src	ollamarunner: Re-enable worst case graph preallocation.	2025-05-02 12:22:47 -07:00
.rsync-filter	ml: add missing cmake property and remove additional CMakeLists.txt (#10310)	2025-04-16 18:56:29 -07:00
LICENSE	next build (#8539)	2025-01-29 15:03:38 -08:00