v0.4.18

Installation

pip install openllm==0.4.18

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

pip install --upgrade openllm==0.4.18

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:0.4.18 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• chore: update lower bound version of bentoml to avoid breakage by @aarnphm in #703
• feat(openai): dynamic model_type registration by @aarnphm in #704

Full Changelog: v0.4.17...v0.4.18

v0.4.17

Installation

pip install openllm==0.4.17

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

pip install --upgrade openllm==0.4.17

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:0.4.17 start HuggingFaceH4/zephyr-7b-beta

Find more information about this release in the CHANGELOG.md

What's Changed

• infra: update generate notes and better local handle by @aarnphm in #701
• fix(backend): correct use variable for backend when initialisation by @aarnphm in #702

Full Changelog: v0.4.16...v0.4.17

v0.4.16

Installation

pip install openllm==0.4.16

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

pip install --upgrade openllm==0.4.16

Usage

All available models: openllm models

To start a LLM: python -m openllm start opt

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P ghcr.io/bentoml/openllm:0.4.16 start opt

To run OpenLLM Clojure UI (community-maintained): docker run -p 8420:80 ghcr.io/bentoml/openllm-ui-clojure:0.4.16

Find more information about this release in the CHANGELOG.md

What's Changed

• feat(ctranslate): initial infrastructure support by @aarnphm in #694
• feat(vllm): bump to 0.2.2 by @aarnphm in #695
• feat(engine): CTranslate2 by @aarnphm in #698
• chore: update documentation about runtime by @aarnphm in #699
• chore: update changelog [skip ci] by @aarnphm in #700

Full Changelog: v0.4.15...v0.4.16

v0.4.15

Installation

pip install openllm==0.4.15

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

pip install --upgrade openllm==0.4.15

Usage

All available models: openllm models

To start a LLM: python -m openllm start opt

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P ghcr.io/bentoml/openllm:0.4.15 start opt

To run OpenLLM Clojure UI (community-maintained): docker run -p 8420:80 ghcr.io/bentoml/openllm-ui-clojure:0.4.15

Find more information about this release in the CHANGELOG.md

What's Changed

• fix(cattrs): strictly lock <23.2 until we upgrade validation logic by @aarnphm in #690
• fix(annotations): check library through find_spec by @aarnphm in #691
• feat: heuristics logprobs by @aarnphm in #692
• chore: update documentation by @aarnphm in #693

Full Changelog: v0.4.14...v0.4.15

v0.4.14

Installation

pip install openllm==0.4.14

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

pip install --upgrade openllm==0.4.14

Usage

All available models: openllm models

To start a LLM: python -m openllm start opt

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P ghcr.io/bentoml/openllm:0.4.14 start opt

To run OpenLLM Clojure UI (community-maintained): docker run -p 8420:80 ghcr.io/bentoml/openllm-ui-clojure:0.4.14

Find more information about this release in the CHANGELOG.md

What's Changed

• fix(dependencies): ignore broken cattrs release by @aarnphm in #689

Full Changelog: v0.4.13...v0.4.14

v0.4.13

Installation

pip install openllm==0.4.13

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

pip install --upgrade openllm==0.4.13

Usage

All available models: openllm models

To start a LLM: python -m openllm start opt

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P ghcr.io/bentoml/openllm:0.4.13 start opt

To run OpenLLM Clojure UI (community-maintained): docker run -p 8420:80 ghcr.io/bentoml/openllm-ui-clojure:0.4.13

Find more information about this release in the CHANGELOG.md

What's Changed

• fix(llm): remove unnecessary check by @aarnphm in #683
• examples: improve instructions and cleanup simple API server by @aarnphm in #684
• fix(build): lock lower version based on each release and update infra by @aarnphm in #686

Full Changelog: v0.4.12...v0.4.13

v0.4.12

Installation

pip install openllm==0.4.12

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

pip install --upgrade openllm==0.4.12

Usage

All available models: openllm models

To start a LLM: python -m openllm start opt

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P ghcr.io/bentoml/openllm:0.4.12 start opt

To run OpenLLM Clojure UI (community-maintained): docker run -p 8420:80 ghcr.io/bentoml/openllm-ui-clojure:0.4.12

Find more information about this release in the CHANGELOG.md

What's Changed

• fix(envvar): explicitly set NVIDIA_DRIVER_CAPABILITIES by @aarnphm in #681
• fix(torch_dtype): correctly infer based on options by @aarnphm in #682

Full Changelog: v0.4.11...v0.4.12

v0.4.11

Installation

pip install openllm==0.4.11

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

pip install --upgrade openllm==0.4.11

Usage

All available models: openllm models

To start a LLM: python -m openllm start opt

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P ghcr.io/bentoml/openllm:0.4.11 start opt

To run OpenLLM Clojure UI (community-maintained): docker run -p 8420:80 ghcr.io/bentoml/openllm-ui-clojure:0.4.11

Find more information about this release in the CHANGELOG.md

What's Changed

• infra: update cbfmt options by @aarnphm in #676
• fix(examples): add support for streaming feature by @aarnphm in #677
• fix: correct set item for attrs >23.1 by @aarnphm in #678
• fix(build): correctly parse default env for container by @aarnphm in #679
• fix(env): correct format environment on docker by @aarnphm in #680

Full Changelog: v0.4.10...v0.4.11

v0.4.10

Installation

pip install openllm==0.4.10

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

pip install --upgrade openllm==0.4.10

Usage

All available models: openllm models

To start a LLM: python -m openllm start opt

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P ghcr.io/bentoml/openllm:0.4.10 start opt

To run OpenLLM Clojure UI (community-maintained): docker run -p 8420:80 ghcr.io/bentoml/openllm-ui-clojure:0.4.10

Find more information about this release in the CHANGELOG.md

What's Changed

• fix(runner): remove keyword args for attrs.get() by @jeffwang0516 in #661
• fix: update notebook by @xianml in #662
• feat(type): provide structured annotations stubs by @aarnphm in #663
• feat(llm): respect warnings environment for dtype warning by @aarnphm in #664
• infra: makes huggingface-hub requirements on fine-tune by @aarnphm in #665
• types: update stubs for remaining entrypoints by @aarnphm in #667
• perf: reduce footprint by @aarnphm in #668
• perf(build): locking and improve build speed by @aarnphm in #669
• docs: add LlamaIndex integration by @aarnphm in #646
• infra: remove codegolf by @aarnphm in #671
• feat(models): Phi 1.5 by @aarnphm in #672
• fix(docs): chatglm support on vLLM by @aarnphm in #673
• chore(loading): include verbose warning about trust_remote_code by @aarnphm in #674
• perf: potentially reduce image size by @aarnphm in #675

New Contributors

• @jeffwang0516 made their first contribution in #661

Full Changelog: v0.4.9...v0.4.10

v0.4.9

Installation

pip install openllm==0.4.9

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

pip install --upgrade openllm==0.4.9

Usage

All available models: openllm models

To start a LLM: python -m openllm start opt

To run OpenLLM within a container environment (requires GPUs): docker run --gpus all -it -P ghcr.io/bentoml/openllm:0.4.9 start opt

To run OpenLLM Clojure UI (community-maintained): docker run -p 8420:80 ghcr.io/bentoml/openllm-ui-clojure:0.4.9

Find more information about this release in the CHANGELOG.md

What's Changed

• infra: update scripts to run update readme automatically by @aarnphm in #658
• chore: update requirements in README.md by @aarnphm in #659
• fix(falcon): remove early_stopping default arguments by @aarnphm in #660

Full Changelog: v0.4.8...v0.4.9