Mike Bonnet b16ff0983d Merge pull request #2344 from mikebonnet/llama-build-less ...

update llama.cpp build flags

2026-01-27 08:30:02 -08:00

..

asahi

don't install ramalama (or anything python-related) into the inference engine images

2025-11-18 06:47:16 -08:00

bats

ci: fix podman-in-podman setup for nvidia GPUs

2025-12-19 11:31:24 -08:00

cann

don't install ramalama (or anything python-related) into the inference engine images

2025-11-18 06:47:16 -08:00

common

stop building and releasing the entrypoint images

2026-01-22 09:44:41 -08:00

cuda

Bump the version of whisper.cpp and llama.cpp

2026-01-07 10:07:58 -05:00

cuda-vllm

Bump the version of whisper.cpp and llama.cpp

2026-01-07 10:07:58 -05:00

e2e

e2e: build a container for running the e2e tests

2026-01-16 14:07:50 -08:00

intel-gpu

update llama.cpp build flags

2026-01-24 00:35:21 -08:00

llama-stack

llama-stack: add missing milvus-lite dependency

2025-12-02 08:29:53 -08:00

musa

don't install ramalama (or anything python-related) into the inference engine images

2025-11-18 06:47:16 -08:00

openvino

Update registry.access.redhat.com/ubi9/ubi Docker tag to v9.7-1769057030

2026-01-26 08:41:20 +00:00

ramalama

install ramalama python libraries in the ramalama and cuda images

2025-12-11 17:43:12 -08:00

ramalama-cli

Move images to fedora 43

2025-11-14 14:29:08 -05:00

ramalama-vllm

More cuda vLLM enablement

2025-07-26 21:40:58 +01:00

rocm

rocm: reduce image size by using a multi-stage build

2026-01-10 10:45:57 -08:00

rocm-fedora

don't install ramalama (or anything python-related) into the inference engine images

2025-11-18 06:47:16 -08:00

scripts

Merge pull request #2344 from mikebonnet/llama-build-less

2026-01-27 08:30:02 -08:00

stable-diffusion

clean up stable-diffusion build

2025-11-18 06:47:16 -08:00