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 in #2369
- stop building the bats image by @mikebonnet in #2370
- Bump to v0.17.0 by @olliewalsh in #2366
Full Changelog: v0.16.0...v0.17.0