v0.5.1

Installation

pip install openllm==0.5.1

To upgrade from a previous version, use the following command:

pip install --upgrade openllm==0.5.1

Usage

To start a LLM: python -m openllm start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

Full Changelog: v0.5.0...v0.5.1

v0.5.0-alpha.15

Installation

pip install openllm==0.5.0-alpha.15

To upgrade from a previous version, use the following command:

pip install --upgrade openllm==0.5.0-alpha.15

Usage

All available models: openllm models

To start a LLM: python -m openllm start HuggingFaceH4/zephyr-7b-beta

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P -v $PWD/data:$HOME/.cache/huggingface/ ghcr.io/bentoml/openllm:0.5.0-alpha.15 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• chore(deps): bump docker/setup-buildx-action from 3.0.0 to 3.2.0 by @dependabot in #941
• chore(deps): bump github/codeql-action from 3.24.3 to 3.24.9 by @dependabot in #939
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #942
• fix(compat): use annotated type from typing_compat by @rudeigerc in #943
• docs: Update high-level messaging by @Sherlock113 in #949
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #947
• chore(deps): bump aquasecurity/trivy-action from 0.18.0 to 0.19.0 by @dependabot in #946
• chore(deps): bump taiki-e/install-action from 2.27.9 to 2.32.9 by @dependabot in #945
• Update README.md by @parano in #964
• chore(deps): bump taiki-e/install-action from 2.32.9 to 2.33.9 by @dependabot in #970
• chore(deps): bump sigstore/cosign-installer from 3.4.0 to 3.5.0 by @dependabot in #954
• chore(deps): bump docker/metadata-action from 5.5.0 to 5.5.1 by @dependabot in #956
• chore(deps): bump actions/setup-python from 5.0.0 to 5.1.0 by @dependabot in #955
• chore(deps): bump pypa/gh-action-pypi-publish from 1.8.11 to 1.8.14 by @dependabot in #958
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #959
• fix: update correct CompletionOutput object by @aarnphm in #973
• chore(deps): bump docker/build-push-action from 5.1.0 to 5.3.0 by @dependabot in #979
• chore(deps): bump docker/login-action from 3.0.0 to 3.1.0 by @dependabot in #978
• chore(deps): bump github/codeql-action from 3.24.9 to 3.25.3 by @dependabot in #977
• chore(deps): bump docker/setup-buildx-action from 3.2.0 to 3.3.0 by @dependabot in #975
• fix: make sure to respect additional parameters parse by @aarnphm in #981
• chore(deps): bump peter-evans/create-pull-request from 5.0.2 to 6.0.5 by @dependabot in #976
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #980
• chore(deps): bump rlespinasse/github-slug-action from 4.4.1 to 4.5.0 by @dependabot in #988
• chore(deps): bump softprops/action-gh-release from 1 to 2 by @dependabot in #987
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #989
• chore(deps): bump taiki-e/install-action from 2.33.9 to 2.33.22 by @dependabot in #985
• chore(deps): bump actions/checkout from 4.1.1 to 4.1.5 by @dependabot in #984
• chore(deps): bump next from 13.4.8 to 14.1.1 by @dependabot in #983
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #994
• chore(deps): bump actions/checkout from 4.1.5 to 4.1.6 by @dependabot in #993
• chore(deps): bump github/codeql-action from 3.25.3 to 3.25.5 by @dependabot in #992
• chore(deps): bump aquasecurity/trivy-action from 0.19.0 to 0.20.0 by @dependabot in #991
• fix(docs): update correct BentoML links by @dennisrall in #995
• tests: add additional basic testing by @aarnphm in #982
• infra: prepare 0.5 releases by @aarnphm in #996
• chore(deps): bump actions/upload-artifact from 3.1.3 to 4.3.3 by @dependabot in #986
• chore(deps): bump actions/download-artifact from 3.0.2 to 4.1.7 by @dependabot in #990
• chore(qol): update CLI options and performance upgrade for build cache by @aarnphm in #997
• feat(ci): running CI on paperspace by @aarnphm in #998
• chore(deps): bump taiki-e/install-action from 2.33.22 to 2.33.34 by @dependabot in #1000

New Contributors

• @rudeigerc made their first contribution in #943
• @dennisrall made their first contribution in #995

Full Changelog: v0.5.0-alpha.1...v0.5.0-alpha.15

v0.5.0

Installation

pip install openllm==0.5.0

To upgrade from a previous version, use the following command:

pip install --upgrade openllm==0.5.0

Usage

To start a LLM: python -m openllm start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #870
• chore(deps): bump taiki-e/install-action from 2.25.9 to 2.26.18 by @dependabot in #899
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #909
• chore(deps): bump github/codeql-action from 3.23.1 to 3.24.3 by @dependabot in #908
• chore(deps): bump sigstore/cosign-installer from 3.3.0 to 3.4.0 by @dependabot in #907
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #931
• feat: 1.2 APIs by @aarnphm in #821
• chore(deps): bump taiki-e/install-action from 2.26.18 to 2.27.9 by @dependabot in #920
• chore(deps): bump next from 13.4.8 to 13.5.1 by @dependabot in #912
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #935
• chore(deps): bump marocchino/sticky-pull-request-comment from 2.8.0 to 2.9.0 by @dependabot in #933
• chore(deps): bump aquasecurity/trivy-action from 0.16.1 to 0.18.0 by @dependabot in #932
• chore(deps): bump docker/setup-buildx-action from 3.0.0 to 3.2.0 by @dependabot in #941
• chore(deps): bump github/codeql-action from 3.24.3 to 3.24.9 by @dependabot in #939
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #942
• fix(compat): use annotated type from typing_compat by @rudeigerc in #943
• docs: Update high-level messaging by @Sherlock113 in #949
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #947
• chore(deps): bump aquasecurity/trivy-action from 0.18.0 to 0.19.0 by @dependabot in #946
• chore(deps): bump taiki-e/install-action from 2.27.9 to 2.32.9 by @dependabot in #945
• Update README.md by @parano in #964
• chore(deps): bump taiki-e/install-action from 2.32.9 to 2.33.9 by @dependabot in #970
• chore(deps): bump sigstore/cosign-installer from 3.4.0 to 3.5.0 by @dependabot in #954
• chore(deps): bump docker/metadata-action from 5.5.0 to 5.5.1 by @dependabot in #956
• chore(deps): bump actions/setup-python from 5.0.0 to 5.1.0 by @dependabot in #955
• chore(deps): bump pypa/gh-action-pypi-publish from 1.8.11 to 1.8.14 by @dependabot in #958
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #959
• fix: update correct CompletionOutput object by @aarnphm in #973
• chore(deps): bump docker/build-push-action from 5.1.0 to 5.3.0 by @dependabot in #979
• chore(deps): bump docker/login-action from 3.0.0 to 3.1.0 by @dependabot in #978
• chore(deps): bump github/codeql-action from 3.24.9 to 3.25.3 by @dependabot in #977
• chore(deps): bump docker/setup-buildx-action from 3.2.0 to 3.3.0 by @dependabot in #975
• fix: make sure to respect additional parameters parse by @aarnphm in #981
• chore(deps): bump peter-evans/create-pull-request from 5.0.2 to 6.0.5 by @dependabot in #976
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #980
• chore(deps): bump rlespinasse/github-slug-action from 4.4.1 to 4.5.0 by @dependabot in #988
• chore(deps): bump softprops/action-gh-release from 1 to 2 by @dependabot in #987
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #989
• chore(deps): bump taiki-e/install-action from 2.33.9 to 2.33.22 by @dependabot in #985
• chore(deps): bump actions/checkout from 4.1.1 to 4.1.5 by @dependabot in #984
• chore(deps): bump next from 13.4.8 to 14.1.1 by @dependabot in #983
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #994
• chore(deps): bump actions/checkout from 4.1.5 to 4.1.6 by @dependabot in #993
• chore(deps): bump github/codeql-action from 3.25.3 to 3.25.5 by @dependabot in #992
• chore(deps): bump aquasecurity/trivy-action from 0.19.0 to 0.20.0 by @dependabot in #991
• fix(docs): update correct BentoML links by @dennisrall in #995
• tests: add additional basic testing by @aarnphm in #982
• infra: prepare 0.5 releases by @aarnphm in #996
• chore(deps): bump actions/upload-artifact from 3.1.3 to 4.3.3 by @dependabot in #986
• chore(deps): bump actions/download-artifact from 3.0.2 to 4.1.7 by @dependabot in #990
• chore(qol): update CLI options and performance upgrade for build cache by @aarnphm in #997
• feat(ci): running CI on paperspace by @aarnphm in #998
• chore(deps): bump taiki-e/install-action from 2.33.22 to 2.33.34 by @dependabot in #1000
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #1002

New Contributors

• @rudeigerc made their first contribution in #943
• @dennisrall made their first contribution in #995

Full Changelog: v0.4.44...v0.5.0

v0.5.0-alpha.1

Release 0.5.0-alpha.1 [generated by GitHub Actions]

v0.5.0-alpha

Release 0.5.0-alpha [generated by GitHub Actions]

v0.4.44

Installation

pip install openllm==0.4.44

To upgrade from a previous version, use the following command:

pip install --upgrade openllm==0.4.44

Usage

All available models: openllm models

To start a LLM: python -m openllm start HuggingFaceH4/zephyr-7b-beta

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P -v $PWD/data:$HOME/.cache/huggingface/ ghcr.io/bentoml/openllm:0.4.44 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• fix: remove vllm dependency for pytorch bento by @larme in #893

Full Changelog: v0.4.43...v0.4.44

v0.4.43

Installation

pip install openllm==0.4.43

To upgrade from a previous version, use the following command:

pip install --upgrade openllm==0.4.43

Usage

All available models: openllm models

To start a LLM: python -m openllm start HuggingFaceH4/zephyr-7b-beta

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P -v $PWD/data:$HOME/.cache/huggingface/ ghcr.io/bentoml/openllm:0.4.43 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• fix: limit BentoML version range by @larme in #881
• chore: bump up bentoml version to 1.1.11 by @larme in #883
• Bump BentoML version in tools by @larme in #884

Full Changelog: v0.4.42...v0.4.43

v0.4.42

Installation

pip install openllm==0.4.42

To upgrade from a previous version, use the following command:

pip install --upgrade openllm==0.4.42

Usage

All available models: openllm models

To start a LLM: python -m openllm start HuggingFaceH4/zephyr-7b-beta

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P -v $PWD/data:$HOME/.cache/huggingface/ ghcr.io/bentoml/openllm:0.4.42 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• docs: Update opt example to ms-phi by @Sherlock113 in #805
• chore(script): run vendored scripts by @aarnphm in #808
• docs: README.md typo by @weibeu in #819
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #818
• chore(deps): bump docker/metadata-action from 5.3.0 to 5.4.0 by @dependabot in #814
• chore(deps): bump taiki-e/install-action from 2.22.5 to 2.23.1 by @dependabot in #813
• chore(deps): bump github/codeql-action from 3.22.11 to 3.22.12 by @dependabot in #815
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #825
• chore(deps): bump crazy-max/ghaction-import-gpg from 6.0.0 to 6.1.0 by @dependabot in #824
• chore(deps): bump taiki-e/install-action from 2.23.1 to 2.23.7 by @dependabot in #823
• docs: Add Llamaindex in freedom to build by @Sherlock113 in #826
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #836
• chore(deps): bump docker/metadata-action from 5.4.0 to 5.5.0 by @dependabot in #834
• chore(deps): bump aquasecurity/trivy-action from 0.16.0 to 0.16.1 by @dependabot in #832
• chore(deps): bump taiki-e/install-action from 2.23.7 to 2.24.1 by @dependabot in #833
• chore(deps): bump vllm to 0.2.7 by @aarnphm in #837
• chore: update discord link by @aarnphm in #838
• improv(package): use python slim base image and let pytorch install cuda by @larme in #807
• fix(dockerfile): conflict deps by @aarnphm in #841
• chore: fix typo in list_models pydoc by @fuzzie360 in #847
• docs: update README.md telemetry code link by @fuzzie360 in #842
• chore(deps): bump taiki-e/install-action from 2.24.1 to 2.25.1 by @dependabot in #846
• chore(deps): bump github/codeql-action from 3.22.12 to 3.23.0 by @dependabot in #844
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #848
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #858
• chore(deps): bump taiki-e/install-action from 2.25.1 to 2.25.9 by @dependabot in #856
• chore(deps): bump github/codeql-action from 3.23.0 to 3.23.1 by @dependabot in #855
• fix: proper SSE handling for vllm by @larme in #877
• chore: set stop to empty list by default by @larme in #878
• fix: all runners sse output by @larme in #880

New Contributors

• @weibeu made their first contribution in #819
• @fuzzie360 made their first contribution in #847

Full Changelog: v0.4.41...v0.4.42

v0.4.41

GPTQ Supports

vLLM backend now support GPTQ with upstream

openlml start TheBloke/Mistral-7B-Instruct-v0.2-GPTQ --backend vllm --quantise gptq

Installation

pip install openllm==0.4.41

To upgrade from a previous version, use the following command:

pip install --upgrade openllm==0.4.41

Usage

All available models: openllm models

To start a LLM: python -m openllm start HuggingFaceH4/zephyr-7b-beta

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P -v $PWD/data:$HOME/.cache/huggingface/ ghcr.io/bentoml/openllm:0.4.41 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• docs: add notes about dtypes usage. by @aarnphm in #786
• chore(deps): bump taiki-e/install-action from 2.22.0 to 2.22.5 by @dependabot in #790
• chore(deps): bump github/codeql-action from 2.22.9 to 3.22.11 by @dependabot in #794
• chore(deps): bump sigstore/cosign-installer from 3.2.0 to 3.3.0 by @dependabot in #793
• chore(deps): bump actions/download-artifact from 3.0.2 to 4.0.0 by @dependabot in #791
• chore(deps): bump actions/upload-artifact from 3.1.3 to 4.0.0 by @dependabot in #792
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #796
• fix(cli): avoid runtime __origin__ check for older Python by @aarnphm in #798
• feat(vllm): support GPTQ with 0.2.6 by @aarnphm in #797
• fix(ci): lock to v3 iteration of actions/artifacts workflow by @aarnphm in #799

Full Changelog: v0.4.40...v0.4.41

v0.4.40

Installation

pip install openllm==0.4.40

To upgrade from a previous version, use the following command:

pip install --upgrade openllm==0.4.40

Usage

All available models: openllm models

To start a LLM: python -m openllm start HuggingFaceH4/zephyr-7b-beta

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P -v $PWD/data:$HOME/.cache/huggingface/ ghcr.io/bentoml/openllm:0.4.40 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• fix(infra): conform ruff to 150 LL by @aarnphm in #781
• infra: update blame ignore to formatter hash by @aarnphm in #782
• perf: upgrade mixtral to use expert parallelism by @aarnphm in #783

Full Changelog: v0.4.39...v0.4.40