phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

clean

Browse source
This commit is contained in:
Swapna Lekkala 2025-11-04 10:59:03 -08:00
parent e6c61cf451
commit d0796388e7
2 changed files with 10 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/docs/providers/eval/index.mdx
View file

@ -2,7 +2,11 @@
description: | description: |
Evaluations Evaluations
<<<<<<< HEAD
Llama Stack Evaluation API for running evaluations on model and agent candidates. Llama Stack Evaluation API for running evaluations on model and agent candidates.
=======
Llama Stack Evaluation API for running evaluations on model and agent candidates."
>>>>>>> eb10a349 (clean)
sidebar_label: Eval sidebar_label: Eval
title: Eval title: Eval
--- ---

13
src/llama_stack/providers/utils/job_scheduler/README.md
View file

@ -62,7 +62,7 @@
## Server Startup Flow ## Server Startup Flow
## Two-Phase Initialization ### Two-Phase Initialization
Separate scheduler initialization into two phases: Separate scheduler initialization into two phases:
- **Phase 1 (`initialize`)**: Load jobs from storage, but don't resume them - **Phase 1 (`initialize`)**: Load jobs from storage, but don't resume them
@ -159,7 +159,7 @@ class VectorIOAdapter:
) )
``` ```
## Behavior ### Behavior
### Case 1: Clean Start (No Jobs) ### Case 1: Clean Start (No Jobs)
```python ```python
@ -246,12 +246,11 @@ class OpenAIVectorStoreMixin:
config: config:
kvstore: { ... } kvstore: { ... }
max_concurrent_jobs: 10 max_concurrent_jobs: 10
Works because:
- Jobs run in the same process via asyncio.create_task()
- In-memory _jobs dict is shared within the process
- Crash recovery works (jobs persist to KVStore)
``` ```
Works because:
- Jobs run in the same process via asyncio.create_task()
- In-memory _jobs dict is shared within the process
- Crash recovery works (jobs persist to KVStore)
--- ---
✅ Multi Worker (Celery Scheduler - Not Implemented Yet) ✅ Multi Worker (Celery Scheduler - Not Implemented Yet)