Repository Issue Activity (beta)

#2831 `rag` erroring with "embedding dimension unknown"

#2815 [packit] Propose downstream failed for release v0.23.0

#2751 [packit] Propose downstream failed for release v0.21.0

#2698 [packit] Propose downstream failed for release v0.20.0

#2788 [packit] Propose downstream failed for release v0.22.0

#136 Dependency Dashboard

#2818 uv: command not found

#2764 KleidiAI CPU backend isn't compiled by default for asahi hosts

#2819 "bad CPU type in executable" when running in Intel mac

#2823 `--backend rocm` is ignored for `ramalama bench`

#2731 `/tmp` still used for storage-heavy operations

#2816 Ramalama sandbox enable multi model support

#2817 Ramalama sandbox --mount feature to point agent to a specific folder on host u want the agent to see

#2813 Depricate Ramalama chat in favor of a default agent

#2798 ramalama does not pass through GPU when run in a toolbox(1), though llama.cpp does

#2559 ramalama sandbox should support connecting to an arbitrary LLM endpoint

#2734 make -ncmoe a first class parameter for llama.cpp runtime

#2800 serve -d to host other than 127.0.0.1 or 0.0.0.0 causes health check timout

#2806 Investigate Multi Modal Support for Ramalama

#2749 replace llama-stack by ogx

#2608 ramalama list: List shortname

#2701 Support for HipFire inference engine

#2792 test_quadlet_and_kube_generation_with_container_registry e2e test failing on fedora 44

#886 CERTIFICATE_VERIFY_FAILED on clean install, Mac Sonoma 14.7.4 with Podman 5.3.2

#2770 install.sh: `curl | bash` for install_uv.sh lacks integrity verification