mirror of
https://github.com/mostlygeek/llama-swap.git
synced 2026-06-09 14:56:34 +02:00
Benson Wong
625b296720
Close inactive issues / close-issues (push) Successful in 7s
Build Unified Docker Image / setup (push) Successful in 3s
Build Containers / build-and-push (cpu) (push) Failing after 14s
Build Containers / build-and-push (cuda) (push) Failing after 12s
Build Containers / build-and-push (cuda13) (push) Failing after 12s
Build Containers / build-and-push (intel) (push) Failing after 11s
Build Containers / build-and-push (musa) (push) Failing after 11s
Build Containers / build-and-push (rocm) (push) Failing after 20s
Build Containers / build-and-push (vulkan) (push) Failing after 11s
Build Containers / delete-untagged-containers (push) Has been skipped
Build Unified Docker Image / build (push) Failing after 13s
Install uv after the cpp tool binaries are copied and before the llama-swap binary, enabling `uv run` usage for Python-based inference backends like vLLM. - add python3-pip to runtime apt installs - add `pip install uv --break-system-packages` after cpp installs fixes #628 Co-authored-by: Claude <noreply@anthropic.com>