phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-26 02:02:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: consolidate most distros into "starter"

Browse source 
* Removes a bunch of distros
* Removed distros were added into the "starter" distribution
* Doc for "starter" has been added
* Partially reverts https://github.com/meta-llama/llama-stack/pull/2482
  since inference providers are disabled by default and can be turned on
  manually via env variable.
* Disables safety in starter distro

Closes: #2502
Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-06-25 16:09:41 +02:00
parent f1c62e0af0
commit 6d8e2c6212
No known key found for this signature in database
132 changed files with 1009 additions and 10845 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/integration/inference/test_openai_completion.py
View file

@ -45,7 +45,7 @@ def skip_if_model_doesnt_support_suffix(client_with_models, model_id):
# To test `fim` ( fill in the middle ) completion, we need to use a model that supports suffix.
# Use this to specifically test this API functionality.
# pytest -sv --stack-config="inference=ollama" \
# pytest -sv --stack-config="inference=starter" \
# tests/integration/inference/test_openai_completion.py \
# --text-model qwen2.5-coder:1.5b \
# -k test_openai_completion_non_streaming_suffix