Docker Model Runner v1.2.1

What's Changed

🚀 Features

• Honor registry mirrors for model pulls and backend downloads (#931) @doringeman
• Add vLLM ROCm Docker variant for AMD GPUs (#917) @dmedovich
• Add MUSA and OpenVINO support using upstream llama.cpp images (#897)
• Run daemon and client from a single binary (#900) @areebahmeddd
• Use official llama.cpp images for Linux (#879)
• Add ContextSize path from FromDirectory (#895) @sathira10
• Extract context size (#866) @sathira10

🐛 Bug Fixes

• Use rm -f to handle missing .py files in llamacpp install (#932)
• Fix gosec g602 error for make validate-all (#911) @areebahmeddd
• Use path.Join instead of filepath.Join for tar entry names (#898)
• Increase timeout for E2E tests to improve stability (#891)
• Update release workflow to prioritize GitHub Release tags (#890)
• Optimize latest release tag retrieval in release.yml (#896) @IgnasiBarrera
• Cap max_tokens in E2E chat helpers to prevent test timeouts (#893)
• Add path sanitization to prevent directory traversal in downloader (#889) @IgnasiBarrera
• Pin Python to 3.12 in vLLM and SGLang build stages (#883)

📦 Dependencies

• Bump llama.cpp to b9209 (#919)
• Bump llama.cpp to b9174 (#918) @krissetto
• Bump llama.cpp to b9102 (#908)
• Bump llama.cpp to b9014 (#901)
• Bump llama.cpp to b8943 (#885)
• Bump docker/cagent-action from 1.5.1 to 1.5.3 (#920)
• Bump docker/cagent-action in the github-actions group (#909)
• Bump openssl (#904)
• Bump the go-modules-root group with 4 updates (#886)
• Bump rustls-webpki (#888)
• Bump the github-actions group with 2 updates (#887)
• Bump openssl (#882)

🔧 Maintenance

• Remove fragile bump-pinata and update-docs jobs from release workflow (#933) @IgnasiBarrera
• Install vLLM ROCm from upstream wheels (#923) @dmedovich
• Update vllm install to use --torch-backend auto (#921)
• Pin golangci-lint version in .versions and read it in CI (#913) @doringeman
• Declare contents: read on ci/e2e-test/integration-test workflows (#914) @arpitjain799
• Bump model-runner Go dependency in pinata during release (#881) @IgnasiBarrera

Full Changelog: v1.1.38...v1.2.1

Docker Model Runner v1.1.38

What's Changed

🐛 Bug Fixes

• fix: pass chat template to vllm-metal backend (#880) @ilopezluna
• fix: install llama-common DLL on Windows shared builds (#878) @ilopezluna

Full Changelog: v1.1.37...v1.1.38

Docker Model Runner v1.1.37

What's Changed

🚀 Features

• feat: add CNCF ModelPack type definitions (#859) @ilopezluna

🐛 Bug Fixes

• fix: add spirv-headers dependency for Vulkan build (#872) @ilopezluna
• fix: improve pull resume reliability and progress bar display on retry (#873) @ericcurtin
• Fix responses goroutine leak (#874) @ilopezluna
• fix: preserve Range header across registry redirects for resumable pulls (#877) @ilopezluna
• fix: allow vllm-metal cache dir in macOS sandbox (#876) @ilopezluna
• fix: keep Python include headers for vllm-metal Metal kernel compilation (#876) @ilopezluna
• fix: pre-compile vllm-metal paged_ops extension in tarball build (#876) @ilopezluna
• fix: allow file-map-executable for vllm-metal cache in macOS sandbox (#876) @ilopezluna

📦 Dependencies

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b8851) (#867) @app/github-actions
• chore(deps): bump the go-modules-root group with 2 updates (#868) @app/dependabot
• chore(deps): bump docker/cagent-action from 1.3.4 to 1.4.1 in the github-actions group (#869) @app/dependabot
• chore: update vllm-metal version to v0.2.0 and vllm version to 0.19.1 (#876) @ilopezluna

🔧 Maintenance

• Remove dead code (#870) @ilopezluna
• chore: pin GitHub Actions to commit SHA (#871) @quentin-laplanche-docker
• refactor: normalize ModelPack config to Docker format in API responses (#875) @ilopezluna

Full Changelog: v1.1.36...v1.1.37

Docker Model Runner v1.1.36

What's Changed

🚀 Features

• feat: add CNCF ModelPack type definitions (#859) @ilopezluna
• feat: enable /logs API endpoint in standalone (Docker CE) mode (#824) @ilopezluna

📦 Dependencies

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b8772) (#855) @github-actions

Full Changelog: v1.1.35...v1.1.36

Docker Model Runner v1.1.35

What's Changed

🚀 Features

• add interactive gateway demo (#849) @ericcurtin

🐛 Bug Fixes

• fix: sandbox permissions (#853) @ilopezluna

Full Changelog: v1.1.34...v1.1.35

Docker Model Runner v1.1.29

What's Changed

🚀 Features

• feat: expose richer model metadata in v1/models (#721) @VedantMadane
• Modelpack support (#791) @ilopezluna
• Add format dduf (#793) @ilopezluna
• Implement DMR log streaming via /logs endpoint (#807) @ilopezluna
• Set backend for DDUF (#809) @ilopezluna

🐛 Bug Fixes

• fix: improve error handling and retry logic in pull operations (#795) @ilopezluna

📦 Dependencies

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b8580) (#804) @app/github-actions
• chore(deps): bump github.com/docker/cli from 29.3.0+incompatible to 29.3.1+incompatible in the go-modules-root group (#805) @app/dependabot
• chore(deps): bump the github-actions group with 2 updates (#806) @app/dependabot
• chore(deps): bump path-to-regexp from 0.1.12 to 0.1.13 in /demos/embeddings in the npm_and_yarn group across 1 directory (#802) @app/dependabot

🔧 Maintenance

• test(e2e): add Linux Docker e2e tests via CI matrix (#790) @doringeman
• Remove unused tests (#792) @ilopezluna
• Resolve merge conflicts and simplify README (#796) @ericcurtin
• Release as latest (#797) @ilopezluna
• ci(release): squeeze extra blank lines in docs go.mod (#799) @doringeman
• test(e2e): add ps and unload tests and explicit backend cleanup (#801) @doringeman
• Add code review style guide (#803) @ericcurtin
• Add leak detector (#811) @ilopezluna
• Change style (#814) @ericcurtin

Full Changelog: v1.1.28...v1.1.29

Docker Model Runner v1.1.28

What's Changed

💥 Breaking Changes

• Make web search opt-in via --websearch flag on run command (#788) @ericcurtin
  • Web search is now disabled by default and must be explicitly enabled with --websearch. Previously it was enabled by default and could only be disabled via DOCKER_MODEL_NO_WEBSEARCH environment variable.

🐛 Bug Fixes

• Remove vLLM x86_64 NVIDIA platform warning from pull compat check (#794) @ericcurtin
• fix(e2e): send SIGINT on teardown to prevent orphan processes (#785) @doringeman

🔧 Maintenance

• ci(release): skip docs PR when CLI reference is unchanged (#786) @doringeman
• Raise Gemini code review threshold to CRITICAL (#789) @ericcurtin

Full Changelog: v1.1.27...v1.1.28

Docker Model Runner v1.1.25

What's Changed

🚀 Features

• add environment variable configuration for Open WebUI to disable auth (#781) @ilopezluna

🐛 Bug Fixes

• set ContentLength when forwarding requests (#717) @ericcurtin
• fix: implement backend resolution for Docker Hub and Hugging Face searches (#754) @ilopezluna
• gracefully fall back when model chat template doesn't support tools (#771) @ericcurtin
• include verbose output alongside errors (#772) @ericcurtin
• Validate realm URL before token exchange (#782) @ilopezluna
• fix(vllm-metal): enable tool calling support in backend args (#783) @doringeman

📦 Dependencies

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b8477) (#774) @github-actions

🔧 Maintenance

• refactor: extract readRequestBody and parseBoolQueryParam helpers (#745) @ericcurtin
• Add dmr dev convenience wrapper (#773) @ericcurtin
• ci(release): add update-docs job to vendor CLI docs in docker/docs (#777) @doringeman
• chore: add dmr binary to gitignore (#778) @doringeman
• test(e2e): add end-to-end tests for inference and CLI (#780) @doringeman

Full Changelog: v1.1.24...v1.1.25

Docker Model Runner v1.1.17

What's Changed

🚀 Features

• feat(backends): add Uninstall method to Backend interface and uninstall-backend endpoint (#770) @doringeman

Full Changelog: v1.1.16...v1.1.17

Docker Model Runner v1.1.14

What's Changed

🐛 Bug Fixes

• fix(standalone): resolve image LD_LIBRARY_PATH instead of literal shell var (#764) @doringeman

🔧 Maintenance

• cmd/cli/commands: use local fork of hooks.PrintNextSteps (#763) @thaJeztah

Full Changelog: v1.1.13...v1.1.14