AI Quick Actions v1.0.3 - llama-cpp container support

oracle / accelerated-data-science

ADS is the Oracle Data Science Cloud Service's python SDK supporting, model ops (train/eval/deploy), along with running workloads on Jobs and Pipeline resources.

https://accelerated-data-science.readthedocs.io/

Universal Permissive License v1.0

87 stars 43 forks source link

AI Quick Actions v1.0.3 - llama-cpp container support #910

Closed VipulMascarenhas closed 2 months ago

VipulMascarenhas commented 2 months ago

Description

This PR covers the following for v1.0.3 release:

Allowing user to register gguf models with llama cpp SMC container.
Add new api to load .gguf files from os path.
Web socket updates/changes.
Load additional fields from container_index json (restricted params to go in next update).
Add new fields for controlling evaluation inference (number of threads, delay etc.) for llama cpp SMC container deployments.
Default shape list will now have BM.GPU.H100.8 option as well.
Added release notes and updated ADS version to 2.11.16.

github-actions[bot] commented 2 months ago

📌 Cov diff with main:

📌 Overall coverage:

github-actions[bot] commented 2 months ago

📌 Cov diff with main:

📌 Overall coverage:

github-actions[bot] commented 2 months ago

⚠️ This PR changed pyproject.toml file. ⚠️

PR Creator must update 📃 THIRD_PARTY_LICENSES.txt, if any 📚 library added/removed in pyproject.toml.
PR Approver must confirm 📃 THIRD_PARTY_LICENSES.txt updated, if any 📚 library added/removed in pyproject.toml.

github-actions[bot] commented 2 months ago

📌 Cov diff with main:

📌 Overall coverage: