Skip to content

Conversation

@ckadner
Copy link
Collaborator

@ckadner ckadner commented Oct 20, 2025

Description

Update links to the Granite FP8 model which is now available on HuggingFace.

https://huggingface.co/ibm-granite/granite-3.3-8b-instruct-FP8

TODO:

  • Update supported models doc
  • Update known model configs file
  • Update runtime config validation code to properly test for quantization configs
  • Update tests to verify we can match locally mounted models by their ModelConfig
  • Verify using PELE

Signed-off-by: Christian Kadner <[email protected]>
@ckadner ckadner merged commit d61305b into vllm-project:main Oct 28, 2025
19 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants