Conversation
|
Hi! This is the friendly automated conda-forge-webservice. It appears you are making a pull request from a branch in your feedstock and not a fork. This procedure will generate a separate build for each push to the branch and is thus not allowed. See our documentation for more details. Please close this pull request and remake it from a fork of this feedstock. Have a great day! |
1 similar comment
|
Hi! This is the friendly automated conda-forge-webservice. It appears you are making a pull request from a branch in your feedstock and not a fork. This procedure will generate a separate build for each push to the branch and is thus not allowed. See our documentation for more details. Please close this pull request and remake it from a fork of this feedstock. Have a great day! |
|
Hi! This is the friendly automated conda-forge-linting service. I wanted to let you know that I linted all conda-recipes in your PR ( Here's what I've got... For recipe/meta.yaml:
This message was generated by GitHub Actions workflow run https://github.com/conda-forge/conda-forge-webservices/actions/runs/27683570316. Examine the logs at this URL for more detail. |
|
FYI, pull requests have to be made from forks, not from branches upstream like here otherwise builds are published on conda-forge. |
This pull request adds a new end-to-end smoke test workflow for GGUF model inference, ensuring that the conda-built package can load, tokenize, run inference, and (optionally) generate embeddings using a small test model. The workflow builds the package, installs it in a fresh environment, downloads a sample GGUF model, and runs a new Python test script to verify core functionality.
New CI workflow for GGUF inference testing:
.github/workflows/test-gguf.ymlto define a GitHub Actions workflow that builds the conda package, installs it in a clean environment, downloads a small GGUF model, and runs an end-to-end test to verify package and model functionality.Test script for GGUF model validation:
test_gguf.py, a Python script that checks the ability to import the package, load a GGUF model, perform tokenization, run inference, and (optionally) generate embeddings, exiting with an error if any step fails.Support tools used: Claude Code Opus 4.8, GitHub Copilot
Checklist
0(if the version changed)conda-smithy(Use the phrase@conda-forge-admin, please rerenderin a comment in this PR for automated rerendering)