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