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

v0.4.39

Installation

pip install openllm==0.4.39

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

pip install --upgrade openllm==0.4.39

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:0.4.39 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• fix(logprobs): correct check logprobs by @aarnphm in #779

Full Changelog: v0.4.38...v0.4.39

v0.4.38

Installation

pip install openllm==0.4.38

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

pip install --upgrade openllm==0.4.38

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:0.4.38 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• fix(mixtral): correct chat templates to remove additional spacing by @aarnphm in #774
• fix(cli): correct set arguments for openllm import and openllm build by @aarnphm in #775
• fix(mixtral): setup hack atm to load weights from pt specifically instead of safetensors by @aarnphm in #776

Full Changelog: v0.4.37...v0.4.38

v0.4.37

Installation

pip install openllm==0.4.37

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

pip install --upgrade openllm==0.4.37

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:0.4.37 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• feat(mixtral): correct support for mixtral by @aarnphm in #772
• chore: running all script when installation by @aarnphm in #773

Full Changelog: v0.4.36...v0.4.37

v0.4.36

Mixtral supports

Supports Mixtral on BentoCloud with vLLM and all required dependencies.

Bento built with openllm now defaults to python 3.11 for this change to work.

Installation

pip install openllm==0.4.36

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

pip install --upgrade openllm==0.4.36

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:0.4.36 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• feat(openai): supports echo by @aarnphm in #760
• fix(openai): logprobs when echo is enabled by @aarnphm in #761
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #767
• chore(deps): bump docker/metadata-action from 5.2.0 to 5.3.0 by @dependabot in #766
• chore(deps): bump actions/setup-python from 4.7.1 to 5.0.0 by @dependabot in #765
• chore(deps): bump taiki-e/install-action from 2.21.26 to 2.22.0 by @dependabot in #764
• chore(deps): bump aquasecurity/trivy-action from 0.14.0 to 0.16.0 by @dependabot in #763
• chore(deps): bump github/codeql-action from 2.22.8 to 2.22.9 by @dependabot in #762
• feat: mixtral support by @aarnphm in #770

Full Changelog: v0.4.35...v0.4.36

v0.4.35

Installation

pip install openllm==0.4.35

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

pip install --upgrade openllm==0.4.35

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:0.4.35 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• chore(deps): bump pypa/gh-action-pypi-publish from 1.8.10 to 1.8.11 by @dependabot in #749
• chore(deps): bump docker/metadata-action from 5.0.0 to 5.2.0 by @dependabot in #751
• chore(deps): bump taiki-e/install-action from 2.21.19 to 2.21.26 by @dependabot in #750
• ci: pre-commit autoupdate [pre-commit.ci] by @pre-commit-ci in #753
• fix(logprobs): explicitly set logprobs=None by @aarnphm in #757

Full Changelog: v0.4.34...v0.4.35

v0.4.34

Installation

pip install openllm==0.4.34

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

pip install --upgrade openllm==0.4.34

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:0.4.34 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• feat(models): Support qwen by @yansheng105 in #742

New Contributors

• @yansheng105 made their first contribution in #742

Full Changelog: v0.4.33...v0.4.34

v0.4.33

Installation

pip install openllm==0.4.33

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

pip install --upgrade openllm==0.4.33

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:0.4.33 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

Full Changelog: v0.4.32...v0.4.33