bentoml/OpenLLM v0.3.4

on GitHub

Installation

pip install openllm==0.3.4

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

pip install --upgrade openllm==0.3.4

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:0.3.4 start opt

To run OpenLLM Clojure UI (community-maintained): docker run -p 8420:80 ghcr.io/bentoml/openllm-ui-clojure:0.3.4

Find more information about this release in the CHANGELOG.md

What's Changed

• dos: fix typo by @Sherlock113 in #305
• fix(serving): vllm bad num_gpus by @alanpoulain in #326
• fix(serialisation): vllm ignore by @aarnphm in #324
• feat: continuous batching with vLLM by @aarnphm in #349
• fix(prompt): correct export extra objects items by @aarnphm in #351

New Contributors

• @alanpoulain made their first contribution in #326

Full Changelog: v0.3.3...v0.3.4