phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-20 19:56:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

In-progress: e2e notebook with partial Eval integration

Browse source
This commit is contained in:
Jash Gulabrai 2025-04-08 14:08:01 -04:00
parent 861962fa80
commit c04ab0133d
19 changed files with 832 additions and 624 deletions
Download patch file Download diff file Expand all files Collapse all files

3
docs/source/distributions/remote_hosted_distro/nvidia.md
View file

@ -7,7 +7,7 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov
|-----|-------------|
| agents | `inline::meta-reference` |
| datasetio | `inline::localfs` |
| eval | `inline::meta-reference` |
| eval | `remote::nvidia` |
| inference | `remote::nvidia` |
| post_training | `remote::nvidia` |
| safety | `remote::nvidia` |
@ -29,6 +29,7 @@ The following environment variables can be configured:
- `NVIDIA_CUSTOMIZER_URL`: NVIDIA Customizer URL (default: `https://customizer.api.nvidia.com`)
- `NVIDIA_OUTPUT_MODEL_DIR`: NVIDIA Output Model Directory (default: `test-example-model@v1`)
- `GUARDRAILS_SERVICE_URL`: URL for the NeMo Guardrails Service (default: `http://0.0.0.0:7331`)
- `NVIDIA_EVALUATOR_URL`: URL for the NeMo Evaluator Service (default: `http://0.0.0.0:7331`)
- `INFERENCE_MODEL`: Inference model (default: `Llama3.1-8B-Instruct`)
- `SAFETY_MODEL`: Name of the model to use for safety (default: `meta/llama-3.1-8b-instruct`)