v0.17.1

What's Changed

• Update dependency huggingface-hub to ~=1.4.0 by @renovate[bot] in #2393
• Update registry.access.redhat.com/ubi9/ubi Docker tag to v9.7-1770238273 by @renovate[bot] in #2397
• Docsite navbar: link logo to ramalama.ai and add docs landing link by @akashWhoCodes in #2391
• Set TORCHINDUCTOR_CACHE_DIR for doc2rag on docker by @olliewalsh in #2402
• Remove invalid cuda version check by @olliewalsh in #2407
• Fix install.sh on Debian and update PATH for uv by @olliewalsh in #2404
• Timeout a hanging e2e test after 15mins by @olliewalsh in #2408
• Bump version to v0.17.1 by @olliewalsh in #2410

New Contributors

• @akashWhoCodes made their first contribution in #2391

Full Changelog: v0.17.0...v0.17.1

v0.17.0

What's Changed

• Adding mikebonnet as ramalama maintainer by @dominikkawka in #2255
• Fix llama-stack oci runtime on CUDA by @olliewalsh in #2256
• Use "with pytest.raises" in tests checking for expected exceptions. by @jwieleRH in #2257
• Fix kube resource label for llama-stack by @olliewalsh in #2261
• ci: fix podman-in-podman setup for nvidia GPUs by @mikebonnet in #2251
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2263
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.7-1766364927 by @red-hat-konflux-kflux-prd-rh03[bot] in #2266
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2264
• Add --quiet/-q flag to silence warnings by @rhatdan in #2259
• chore(deps): update konflux references to 0b10508 by @red-hat-konflux-kflux-prd-rh03[bot] in #2270
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2271
• Add e2e pytest test for info command by @telemaco in #2268
• Add e2e pytest test for convert command by @telemaco in #2267
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.7-1767674301 by @red-hat-konflux-kflux-prd-rh03[bot] in #2276
• chore: add CLAUDE.md by @nathan-weinberg in #2274
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2273
• Update maintainers in pyproject.toml. by @jwieleRH in #2272
• Fix quadlet generation for multi-part models by @rhatdan in #2248
• chore typing and some bug fixes by @ieaves in #2241
• 056-artifact.bats: fix the expected return code for OSErrors by @mikebonnet in #2279
• Add type annotations for BaseEngine and info_cli by @jwieleRH in #2280
• Add e2e pytest test for pull command by @telemaco in #2227
• Set GGML_CPU_ALL_VARIANTS for llama-cpp builds by @olliewalsh in #2281
• Bump the version of whisper.cpp and llama.cpp by @rhatdan in #2278
• ci: install coreutils on macos by @olliewalsh in #2283
• Stop pinning setuptools version in pyproject.toml by @olliewalsh in #2284
• CI: fix race in test_pull.py::test_pull_with_registry by @olliewalsh in #2294
• Add e2e pytest test for rag command by @telemaco in #2260
• Upgrade rag-requirements by @engelmi in #2293
• Add e2e pytest test for inspect command by @telemaco in #2269
• cuda: update compiler to gcc 14 by @mikebonnet in #2288
• Use correct merge repo in konflux PR pipeline by @olliewalsh in #2300
• Add github star history graph to README by @olliewalsh in #2298
• publish artifacts to pypi when a new Github release is published by @mikebonnet in #2301
• chore(deps): update dependency huggingface-hub to ~=1.3.1 by @red-hat-konflux-kflux-prd-rh03[bot] in #2297
• CI: retry ollama pull by @olliewalsh in #2290
• rocm: reduce image size by using a multi-stage build by @mikebonnet in #2246
• Add e2e pytest test for mlx by @telemaco in #2307
• [skip-ci] Update step-security/harden-runner action to v2.14.0 by @renovate[bot] in #2304
• [skip-ci] Update actions/download-artifact action to v7 by @renovate[bot] in #2305
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2306
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2303
• Fix race in chat initialization by @olliewalsh in #2313
• Use /var/tmp for konflux tests by @olliewalsh in #2315
• konflux: build e2e image and add integration test by @mikebonnet in #2317
• Fix konflux git-clone merge issue for renovate by @olliewalsh in #2329
• Fix e2e konflux tests by @olliewalsh in #2331
• e2e: create TEMP_DIR when script is run on the VM by @mikebonnet in #2334
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.7-1768785530 by @renovate[bot] in #2327
• ci: fix the ollama installer by @mikebonnet in #2336
• macOS installer: fixes and updates by @mikebonnet in #2302
• chore(deps): update dependency wheel to ~=0.46.3 by @red-hat-konflux-kflux-prd-rh03[bot] in #2337
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2326
• konflux: use large disk instances for e2e tests by @mikebonnet in #2341
• Fix remaining issues with Windows path handling and file URIs by @olliewalsh in #2333
• Work around race condition in test/e2e/test_serve.py::test_serve_and_stop by @olliewalsh in #2342
• Fix handling of alternative inference engines by @olliewalsh in #2311
• Bump llama.cpp and whisper.cpp version by @olliewalsh in #2310
• Add Provider Abstraction with support for Hosted API Calls by @ieaves in #2192
• Add benchmark metrics persistence by @ieaves in #2339
• stop building and releasing the entrypoint images by @mikebonnet in #2340
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2321
• Lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2346
• [skip-ci] Update step-security/harden-runner action to v2.14.1 by @renovate[bot] in #2347
• Update react monorepo to v19.2.4 by @red-hat-konflux-kflux-prd-rh03[bot] in #2350
• Update registry.access.redhat.com/ubi9/ubi Docker tag to v9.7-1769057030 by @renovate[bot] in #2348
• update llama.cpp build flags by @mikebonnet in #2344
• update to black 26.1 and fix formatting by @mikebonnet in #2335
• docs: fix docsite build by escaping angle bracket and curly bracket by @mikebonnet in #2354
• Update registry.access.redhat.com/ubi9/ubi Docker tag to v9.7-1769417801 by @red-hat-konflux-kflux-prd-rh03[bot] in #2349
• remove whisper.cpp from all images by @mikebonnet in #2357
• Reduce CI load and fix unreliable tests by @olliewalsh in #2358
• Improving cold start time on cli invocation. by @ieaves in #2309
• Fix slow test_run_model_with_prompt on windows by @olliewalsh in #2363
• Download safetensors models from huggingface.co with https. by @jwieleRH in #2224
• [trivial] correctly omit test_serve_api by @olliewalsh in #2364
• Use default (auto) value for llama.cpp flash-attn by @olliewalsh in #2359
• Bump llama.cpp version by @olliewalsh in #2365
• Restores comment from #2309 by @ieaves in #2371
• Remove generated doc files. by @jwieleRH in #2372
• Update Konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2386
• Lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2388
• use multi-stage builds for all images by @mikebonnet in #2368
• Update all dependencies in the -rag images to their latest versions by @mikebonnet ...

v0.16.0

What's Changed

• Add Windows E2E test suite with Podman support by @rhatdan in #2159
• chore(deps): update dependency huggingface-hub to ~=1.2.1 by @renovate[bot] in #2218
• chore(deps): update pre-commit hook psf/black to v25.12.0 by @red-hat-konflux-kflux-prd-rh03[bot] in #2223
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2222
• [skip-ci] Update actions/setup-python action to v6 by @renovate[bot] in #2220
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2219
• Enhance Ollama cache lookup by @telemaco in #2216
• [skip-ci] Update actions/upload-artifact action to v5 by @renovate[bot] in #2221
• Fix windows model store names by @olliewalsh in #2228
• Fix Python 3.10 by @olliewalsh in #2230
• packit: run no-rpm tests on V100 gpus by @mikebonnet in #2231
• chore(deps): update react monorepo to v19.2.2 by @renovate[bot] in #2234
• ci: cleanup unnecessary/obsolete workflows by @mikebonnet in #2233
• install ramalama python libraries in the ramalama and cuda images by @mikebonnet in #2236
• fix(deps): update react monorepo to v19.2.3 by @red-hat-konflux-kflux-prd-rh03[bot] in #2235
• Added --sort and --order option to ramalama ls by @engelmi in #2238
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2242
• [skip-ci] Update actions/upload-artifact action to v6 by @renovate[bot] in #2240
• Windows support part 2 by @olliewalsh in #2239
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2244
• Add support for converting to OCI artifacts by @rhatdan in #2046
• Revert "Workaround for CUDA image not pointing to libcuda.so.1 in ld.so.conf" by @olliewalsh in #2247
• Add comprehensive uninstall instructions to README by @rhatdan in #2245
• Fix removing blobs when hardlink/copy is used by @olliewalsh in #2249
• Bump to v0.16.0 by @olliewalsh in #2254

Full Changelog: v0.15.0...v0.16.0

v0.15.0

What's Changed

• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2095
• RamaLama Contributor ladder by @dominikkawka in #2090
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2099
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2097
• Switch DEFAULT_PORT_RANGE to use 100 ports by @rhatdan in #2091
• konflux: re-enable s390x builds by @mikebonnet in #2102
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2103
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2106
• Fix HuggingFace login/logout CLI commands by @rhatdan in #2107
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2112
• chore(deps): update dependency huggingface-hub to ~=1.1.2 by @red-hat-konflux-kflux-prd-rh03[bot] in #2109
• Add community meetup references to readme by @ieaves in #2111
• updates registry url link by @ieaves in #2115
• Added mapping of https to specific transport by @engelmi in #2117
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2116
• Add GPU-specific VLLM image support by @rhatdan in #2119
• Fix nix flake by @poelzi in #2121
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2123
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2122
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2127
• Disable preview flag for black formatter by @olliewalsh in #2134
• fix: Prevent duplicate CLI debug logs by stopping logger propagation by @kush-gupt in #2135
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2131
• Add e2e pytest test for serve command by @telemaco in #2085
• chore(deps): update pre-commit hook psf/black to v25.11.0 by @red-hat-konflux-kflux-prd-rh03[bot] in #2128
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.7-1762180182 by @red-hat-konflux-kflux-prd-rh03[bot] in #2139
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2140
• chore(deps): update dependency pytest to v9 by @red-hat-konflux-kflux-prd-rh03[bot] in #2125
• Fix-up ref file path field when it has been moved by @olliewalsh in #2146
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.7-1762948793 by @renovate[bot] in #2143
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2144
• Fix RAG mount option incompatibility with Docker by @rhatdan in #2150
• Report when service exits unexpectedly during ramalama run by @rhatdan in #2130
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2153
• Move images to fedora 43 by @rhatdan in #1996
• Add Windows path support for Docker/Podman volume mounts by @rhatdan in #2154
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2156
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2157
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2160
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.7-1763340522 by @red-hat-konflux-kflux-prd-rh03[bot] in #2163
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2161
• renovate: only update the docsite lockfiles once a week by @mikebonnet in #2164
• bats: add procps-ng by @mikebonnet in #2166
• chore(config): migrate renovate config by @red-hat-konflux-kflux-prd-rh03[bot] in #2167
• fix: addressed rag read write error and timeout error by @bmahabirbu in #2168
• don't install ramalama (or anything python-related) into the inference engine images by @mikebonnet in #2169
• konflux: on PRs, only build images when there is a change that's relevant to the image content by @mikebonnet in #2170
• automatic chat summerizor to prevent context growth by @rhatdan in #2165
• Do not clobber all default images when one is set in the config file by @olliewalsh in #2171
• Add SOCKS proxy support by @rhatdan in #2035
• rag: update to Fedora 43 by @mikebonnet in #2173
• Implement ServerMonitor class by @rhatdan in #2155
• Remove unused Python functions by @jwieleRH in #2175
• Make http_client retry logic configurable and fix off-by-one by @olliewalsh in #2149
• Feat/log level by @ieaves in #2152
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2183
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2178
• Adds auto rebuild for documentation by @ieaves in #2177
• Introduce e2e pytest testing guide by @telemaco in #2141
• [skip-ci] Update actions/setup-node action to v6 by @renovate[bot] in #2184
• Add test to verify CONFIG options are documented by @rhatdan in #2158
• Add self-contained macOS installer package by @rhatdan in #2036
• [skip-ci] Update actions/checkout action to v6 by @renovate[bot] in #2176
• Add /approve command workflow for PR approvals by @rhatdan in #2120
• [skip-ci] Update actions/github-script action to v8 by @renovate[bot] in #2186
• konflux: simplify integration tests and image pushes by @mikebonnet in #2188
• chore(deps): update dependency node to v24 by @renovate[bot] in #2191
• [skip-ci] Update softprops/action-gh-release action to v2 by @renovate[bot] in #2190
• [skip-ci] Update actions/upload-artifact action to v5 - autoclosed by @renovate[bot] in #2189
• [skip-ci] Update actions/setup-python action to v6 by @renovate[bot] in #2187
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2198
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2196
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.7-1764163501 by @red-hat-konflux-kflux-prd-rh03[bot] in #2194
• Pass through reasoning_content in RAG proxy streaming by @csoriano2718 in #2179
• Handle non-zero return code from nvidia-smi in check_nvidia() by @olliewalsh in #2200
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.7-1764578509 by @red-hat-konflux-kflux-prd-rh03[bot] in #2199
• e2e: fix llama-stack test failure caused by lack of disk space by @mikebonnet in #2202
• Update all dependencies in the -rag images to their latest versions by @mikebonnet in #2195
• llama-stack: add missing milvus-lite dependency by @mikebonnet in #2203
• Fix test_help.py:test_default_image() white space handling. by @jwieleRH in htt...

v0.14.0

What's Changed

• Docsite builds remove extraneous manpage number labels by @ieaves in #2037
• Bump to latest llama.cpp and whisper.cpp by @rhatdan in #2039
• Added inference specification files to info command by @engelmi in #2049
• Update docusaurus monorepo to v3.9.2 by @red-hat-konflux-kflux-prd-rh03[bot] in #2055
• Pin macos CI to python <3.14 until mlx is updated by @olliewalsh in #2051
• Added --max-tokens to llama.cpp inference spec by @engelmi in #2057
• Lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2056
• Prefer the embedded chat template for ollama models by @olliewalsh in #2040
• Set gguf quantization default to Q4_K_M by @engelmi in #2050
• Update dependency huggingface-hub to ~=0.36.0 by @red-hat-konflux-kflux-prd-rh03[bot] in #2059
• Update Konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2044
• Lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2060
• docker: fix list command for oci images when running in a non-UTC timezone by @mikebonnet in #2067
• Update dependency huggingface-hub to v1 by @renovate[bot] in #2066
• Fix AMD GPU image selection on arm64 for issue #2045 by @rhatdan in #2048
• run RAG operations in a separate container by @mikebonnet in #2053
• konflux: merge before building/testing PRs by @mikebonnet in #2069
• fix "ramalama rag" under docker by @mikebonnet in #2068
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2070
• Renaming huggingface-cli -> hf by @Yarboa in #2047
• Added Speaking and Advocacy heading for CONTRIBUTING.md by @dominikkawka in #2073
• Fix the rpm name in docs by @olliewalsh in #2083
• Update SECURITY.md. Use github issues for security vulnerabilities by @rhatdan in #2077
• Improving ramalama rag section in README.md by @jpodivin in #2076
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2074
• fix up type checking and add it to GitHub CI by @mikebonnet in #2075
• konflux: disable builds on s390x by @mikebonnet in #2087
• Bump llama.cpp and whisper.cpp by @rhatdan in #2071
• chore(deps): lock file maintenance by @red-hat-konflux-kflux-prd-rh03[bot] in #2088
• Add --port flag to ramalama run command by @rhatdan in #2082
• rag: keep the versions of gguf and convert_hf_to_gguf.py in sync by @mikebonnet in #2092
• Bump to v0.14.0 by @rhatdan in #2093

New Contributors

• @Yarboa made their first contribution in #2047
• @dominikkawka made their first contribution in #2073
• @jpodivin made their first contribution in #2076

Full Changelog: v0.13.0...v0.14.0

v0.13.0

What's Changed

• Reintroduce readme updates and add additional documentation by @ieaves in #1987
• feat: support safetensors-only repos across runtimes by @kush-gupt in #1976
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #1984
• [skip-ci] Update astral-sh/setup-uv action to v7 by @renovate[bot] in #2006
• Remove tag in model name for health check by @engelmi in #2008
• Add safetensor snapshot file type by @engelmi in #2009
• Fixes default engine detection for OSX users by @ieaves in #2010
• Don't attempt to relabel image mounts by @rhatdan in #2012
• Link to Ollama registry catalong and fix capitalizations by @rhatdan in #2011
• add support for split model file url by @fozzee in #2001
• Update pre-commit hook pycqa/isort to v7 by @red-hat-konflux-kflux-prd-rh03[bot] in #2021
• Update dependency isort to v7 by @red-hat-konflux-kflux-prd-rh03[bot] in #2020
• Update Konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #2018
• Adds dependency group so uv automatically provisions dev dependencies by @ieaves in #2015
• Always chosen port passed via CLI parameter by @engelmi in #2013
• Daemon bugfix for docker users and better pull config handling by @ieaves in #2005
• Update registry.access.redhat.com/ubi9/ubi Docker tag to v9.6-1760340943 by @red-hat-konflux-kflux-prd-rh03[bot] in #2023
• Search the inference spec files in the source directory by @kpouget in #2014
• docs: Update README with correct MLX install instructions by @kush-gupt in #2024
• Added data-files path to default config dirs list by @engelmi in #2028
• Template conversion system and messages template wrapping for Go templates by @ieaves in #1947
• Fix model paths when running with --nocontainer by @olliewalsh in #2030
• Add NVIDIA GPU support to quadlet generation for ramalama serve by @wang7x in #1955
• build_rag.sh: add libraries required by opencv-python by @mikebonnet in #2031
• Bump to v0.13.0 by @rhatdan in #2029

New Contributors

• @wang7x made their first contribution in #1955

Full Changelog: v0.12.4...v0.13.0

v0.12.4

What's Changed

• fix: split model regex match model without path by @fozzee in #1952
• konflux: fix creation of the PipelineRun when a tag is pushed by @mikebonnet in #1961
• Add e2e pytest test for list and rm commands by @telemaco in #1949
• konflux: test the cuda image on NVIDIA hardware by @mikebonnet in #1800
• fix: use OpenVINO 2025.3 by @jeffmaury in #1968
• chore(deps): update pre-commit hook psf/black to v25.9.0 by @red-hat-konflux-kflux-prd-rh03[bot] in #1965
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #1964
• chore(config): migrate renovate config by @red-hat-konflux-kflux-prd-rh03[bot] in #1966
• Fix cuda-vllm image build steps by @mcornea in #1963
• fix(intel): detect xe driver by @futursolo in #1980
• chore(deps): update konflux references to abf231c by @red-hat-konflux-kflux-prd-rh03[bot] in #1975
• Add e2e pytest test for help command by @telemaco in #1973
• fix: rename file with : in name by @jeffmaury in #1972
• chore(deps): update dependency macos to v15 by @renovate[bot] in #1970
• Fix handling of API_KEY in ramalama chat by @rhatdan in #1958
• Inference engine spec by @engelmi in #1959
• Add e2e pytest test for run command by @telemaco in #1978
• Add perplexity and bench by @engelmi in #1986
• Update react monorepo to v19.2.0 by @renovate[bot] in #1992
• Update pre-commit hook pycqa/isort to v6.1.0 by @red-hat-konflux-kflux-prd-rh03[bot] in #1991
• Fix --exclude-dir arguments to grep in Makefile and add .tox. by @jwieleRH in #1990
• updates docsite and adds docsite to the make docs process by @ieaves in #1988
• Fix typo in llama.cpp engine spec by @olliewalsh in #1998
• chore: update demo script with RAG and mcp based on dev conf presenta… by @bmahabirbu in #1994
• Fix llama.cpp build instruction set by @olliewalsh in #2000
• Add unified --max-tokens CLI argument for output token limiting by @rhatdan in #1982
• Bump the versions of llama.cpp and whisper.cpp by @rhatdan in #1999
• Bump to v0.12.4 by @rhatdan in #2003

New Contributors

• @fozzee made their first contribution in #1952
• @jeffmaury made their first contribution in #1968
• @futursolo made their first contribution in #1980

Full Changelog: v0.12.3...v0.12.4

v0.12.3

What's Changed

• konflux: release images when a tag is pushed to the git repo by @mikebonnet in #1926
• konflux: build ramalama images for s390x and ppc64le by @mikebonnet in #1842
• konflux: run clamav-scan as a matrixed task by @mikebonnet in #1922
• s390x: switch to a smaller bigendian model for testing by @mikebonnet in #1930
• --flash-attn requires an option in llama-server now by @rhatdan in #1928
• Pass the encoding argument to run_cmd(). by @jwieleRH in #1931
• Improve NVIDIA CDI check. by @jwieleRH in #1903
• [ci] Update repo for ubuntu podman 5 by @olliewalsh in #1940
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #1932
• chore(deps): update dependency huggingface-hub to ~=0.35.0 by @renovate[bot] in #1935
• fix: with the new llama.cpp version and chat templates rag_framework … by @bmahabirbu in #1937
• Introduce tox for testing and add e2e framework by @telemaco in #1938
• docs: revert incorrect docs changes by @cdoern in #1936
• Add bats test to cover docker-compose in serve by @abhibongale in #1934
• konflux: set the source-repo-url annotation on the override Snapshot by @mikebonnet in #1941
• Add Compose docs by @abhibongale in #1943
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.6-1758184894 by @renovate[bot] in #1944
• Adds a roadmap document for tracking future work and goals by @ieaves in #1893
• konflux: handle "incoming" events when creating override Snapshots by @mikebonnet in #1945
• added mcp to chat by @bmahabirbu in #1923
• introduced some qol fixed for standard python mcp client by @bmahabirbu in #1953
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #1954
• Add e2e pytest workflows to Github CI by @telemaco in #1950
• Add e2e pytest test for bench command by @telemaco in #1942
• Reorganize transports and add new rlcr transport option by @ieaves in #1907
• Bump to v0.12.3 by @rhatdan in #1956

New Contributors

• @cdoern made their first contribution in #1936

Full Changelog: v0.12.2...v0.12.3

v0.12.2

What's Changed

• Add Docker Compose generator by @abhibongale in #1839
• Catch KeyError exceptions by @rhatdan in #1867
• Fallback to default image when CUDA version is out of date by @rhatdan in #1871
• Changed from google-chrome to firefox by @AlexonOliveiraRH in #1876
• Revert back to ollama granite-code models by @olliewalsh in #1875
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.6-1756799158 by @renovate[bot] in #1887
• fix(deps): update dependency @mdx-js/react to v3.1.1 by @renovate[bot] in #1885
• Don't print llama stack api endpoint info unless --debug is passed by @booxter in #1881
• feat(script): add browser override and improve service startup flow by @AlexonOliveiraRH in #1879
• tests: generate tmpdir store for ollama pull testcase by @booxter in #1891
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #1884
• [skip-ci] Update actions/stale action to v10 by @renovate[bot] in #1896
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.6-1756915113 by @red-hat-konflux-kflux-prd-rh03[bot] in #1895
• Added the GGUF field tokenizer.chat_template for getting chat template by @engelmi in #1890
• Suppress stderr when chatting without container by @booxter in #1880
• konflux: stop building unnecessary images by @mikebonnet in #1897
• Readme updates and python classifiers by @ieaves in #1894
• Update versions of llama.cpp and whisper.cpp by @rhatdan in #1874
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #1906
• Extended inspect command by --get option with auto-complete by @engelmi in #1889
• Allow running ramalama without a GPU by @kpouget in #1909
• Add tests for --device none by @kpouget in #1911
• Bump to latest version of llama.cpp by @rhatdan in #1910
• Initial model swap work by @engelmi in #1807
• Fix ramalama run with prompt index error by @engelmi in #1913
• Fix the application of codespell in "make validate". by @jwieleRH in #1904
• Do not set the ctx-size by default by @rhatdan in #1915
• Use Hugging Face models for tinylama and smollm:135 by @olliewalsh in #1916
• build_rag.sh: install mistral-common for convert_hf_to_gguf.py by @mikebonnet in #1925
• Bump to v0.12.2 by @rhatdan in #1912

New Contributors

• @abhibongale made their first contribution in #1839
• @AlexonOliveiraRH made their first contribution in #1876

Full Changelog: v0.12.1...v0.12.2

v0.12.1

What's Changed

• konflux: remove ecosystem tests by @mikebonnet in #1841
• konflux: migrate to per-component service accounts by @mikebonnet in #1840
• Bats test fixes by @olliewalsh in #1847
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #1851
• Add support for huggingface split GGUF models by @olliewalsh in #1848
• Fix progress bar not reaching 100% by @olliewalsh in #1846
• Use correct chat template file for ollama models by @olliewalsh in #1856
• fix: Don't use non-portable errno.{EMEDIUMTYPE,ENOMEDIUM} by @booxter in #1850
• Make the container build system more flexible by @kpouget in #1854
• Fix deepseek-r1 chat template conversion by @olliewalsh in #1858
• chore(deps): update registry.access.redhat.com/ubi9/ubi docker tag to v9.6-1755678605 by @red-hat-konflux-kflux-prd-rh03[bot] in #1863
• DNM: ci test by @olliewalsh in #1862
• Fix python environment in ci jobs by @olliewalsh in #1861
• feat: added wait logic for rag_framework fixed doc2rag file and added… by @bmahabirbu in #1761
• chore(deps): update konflux references by @red-hat-konflux-kflux-prd-rh03[bot] in #1865
• Bump to v0.12.1 by @rhatdan in #1866

New Contributors

• @booxter made their first contribution in #1850
• @kpouget made their first contribution in #1854

Full Changelog: v0.12.0...v0.12.1