COMMITS
/ backend/Dockerfile.llama-cpp May 9, 2026
L
ci: refactor llama-cpp variant Dockerfiles to consume prebuilt base-grpc images (PR 2/2) (#9738)
LocalAI [bot] committed
E
ci(llama-cpp): add BuildKit ccache mount to the compile step
Ettore Di Giacinto committed
May 3, 2026
E
feat(ci): allow routing apt traffic through an alternate Ubuntu mirror (#9650)
Ettore Di Giacinto committed
April 24, 2026
A
fix: add hipblaslt library (#9541)
Andreas Egli committed
April 18, 2026
K
fix(rocm): add gfx1151 support and expose AMDGPU_TARGETS build-arg (#9410)
Keith Mattix II committed
April 12, 2026
E
feat(rocm): bump to 7.x (#9323)
Ettore Di Giacinto committed
January 12, 2026
E
chore(vulkan): bump vulkan-sdk to 1.4.335.0 (#7981)
Ettore Di Giacinto committed
January 8, 2026
E
chore(ci): roll back l4t-cuda12 configurations (#7935)
Ettore Di Giacinto committed
January 7, 2026
C
feat: enable Vulkan arm64 image builds (#7912)
Copilot committed
January 6, 2026
R
chore: Update to Ubuntu24.04 (cont #7423) (#7769)
Richard Palethorpe committed
C
fix: BMI2 crash on AVX-only CPUs (Intel Ivy Bridge/Sandy Bridge) (#7864)
coffeerunhobby committed
December 3, 2025
E
chore(ci): add wget to llama-cpp docker image builder
Ettore Di Giacinto committed
E
chore(ci): small fixups to build arm64 images
Ettore Di Giacinto committed
E
chore(ci): minor fixup
Ettore Di Giacinto committed
E
chore(ci): only install runtime libs needed on arm64
Ettore Di Giacinto committed
October 24, 2025
C
fix: llama dockerfile make package (#6694)
Chakib Benziane committed
July 18, 2025
E
feat: do not bundle llama-cpp anymore (#5790)
Ettore Di Giacinto committed