chore: remove dead Llama SKU catalog and broken generate_prompt_format script.#5957
Open
derekhiggins wants to merge 1 commit into
Open
chore: remove dead Llama SKU catalog and broken generate_prompt_format script.#5957derekhiggins wants to merge 1 commit into
derekhiggins wants to merge 1 commit into
Conversation
derekhiggins
requested review from
bbrowning,
cdoern,
franciscojavierarceo,
leseb,
mattf and
raghotham
as code owners
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
derekhiggins
changed the title
…t script The SKU files (sku_list.py, sku_list_download.py, sku_types.py) and scripts/generate_prompt_format.py became dead code after the inline vLLM provider was removed in ogx-ai#2824 and the model implementation was deleted in ogx-ai#4829/ogx-ai#4871. The remaining consumer in providers/utils/inference built a HuggingFace-repo-to-descriptor mapping that no provider ever populated. Closes ogx-ai#5956 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Derek Higgins <derekh@redhat.com>
derekhiggins
force-pushed
the
chore/remove-dead-sku-catalog
branch
from
a91ae1d to
a34b6ef
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
sku_list.py,sku_list_download.py,sku_types.py)scripts/generate_prompt_format.py(imports module deleted in chore: prune llama_stack.models package #4829)ALL_HUGGINGFACE_REPOS_TO_MODEL_DESCRIPTORmapping andllama_modelmetadata validation frommodel_registry.pyProviderModelEntry.llama_modelfield andget_llama_model()method (no provider sets this)Context
The SKU files supported the inline vLLM provider (deleted in #2824) and Ollama's hardcoded model entries (removed in #1107/#2916). After those removals, no runtime code consumed this catalog. PR #4838 cleaned up most usage but missed the HF-repo mapping in
providers/utils/inference.The code also contained two confirmed bugs (ambiguous HF repo lookup for 405B variants, broken
is_instruct_modelproperty) that were never hit because nothing calls the affected code paths.Test plan
uv run pytest tests/unit/ -x --tb=shortpasses (325 tests, same as before)uv run pre-commit run --all-filespassesCloses #5956