phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 18:00:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
3084 commits 55 branches 148 tags 103 MiB
Commit graph

10 commits

Author SHA1 Message Date
Derek Higgins
1562277cfd
ci: test adjustments for Qwen3-0.6B (#3978) 
Without this hint Qwen3-0.6B tends to reply with the full name
and sometimes doesn't reply with the correct drafted year.

---------

Signed-off-by: Derek Higgins <derekh@redhat.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
 2025-11-03 12:19:35 -08:00
Luis Tomas Bolivar
f18b5eb537
fix: Avoid BadRequestError due to invalid max_tokens (#3667) 
This patch ensures if max tokens is not defined, then is set to None
instead of 0 when calling openai_chat_completion. This way some
providers (like gemini) that cannot handle the `max_tokens = 0` will not
fail

Issue: #3666
 2025-10-27 09:27:21 -07:00
Ashwin Bharambe
0e57233a0a
chore(misc): update datasets, benchmarks to use alpha, beta prefixes (#3891) 
This will be landed together with
https://github.com/llamastack/llama-stack-client-python/pull/282 (hence
CI will be red on this one.)

I have verified locally that tests pass with the updated version of the
client-sdk.
 2025-10-22 15:26:35 -07:00
Ashwin Bharambe
79bed44b04
fix(tests): ensure test isolation in server mode (#3737) 
Propagate test IDs from client to server via HTTP headers to maintain
proper test isolation when running with server-based stack configs.
Without
this, recorded/replayed inference requests in server mode would leak
across
tests.

Changes:
- Patch client _prepare_request to inject test ID into provider data
header
- Sync test context from provider data on server side before storage
operations
- Set LLAMA_STACK_TEST_STACK_CONFIG_TYPE env var based on stack config
- Configure console width for cleaner log output in CI
- Add SQLITE_STORE_DIR temp directory for test data isolation
 2025-10-08 12:03:36 -07:00
Ashwin Bharambe
045a0c1d57
feat(tests): implement test isolation for inference recordings (#3681) 
Uses test_id in request hashes and test-scoped subdirectories to prevent
cross-test contamination. Model list endpoints exclude test_id to enable
merging recordings from different servers.

Additionally, this PR adds a `record-if-missing` mode (which we will use
instead of `record` which records everything) which is very useful.

🤖 Co-authored with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude <noreply@anthropic.com>
 2025-10-04 11:34:18 -07:00
Ashwin Bharambe
73de235ef1 fix(eval): use client.alpha for eval tests 2025-09-30 13:02:33 -07:00
Xi Yan
baf68c665c
fix: fix jobs api literal return type (#1757) 
# What does this PR do?

- We cannot directly return a literal type

> Note: this is not final jobs API change

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
<img width="837" alt="image"
src="https://github.com/user-attachments/assets/18a17561-35f9-443d-987d-54afdd6ff40c"
/>


[//]: # (## Documentation)
 2025-03-21 14:04:21 -07:00
Xi Yan
5287b437ae
feat(api): (1/n) datasets api clean up (#1573) 
## PR Stack
- https://github.com/meta-llama/llama-stack/pull/1573
- https://github.com/meta-llama/llama-stack/pull/1625
- https://github.com/meta-llama/llama-stack/pull/1656
- https://github.com/meta-llama/llama-stack/pull/1657
- https://github.com/meta-llama/llama-stack/pull/1658
- https://github.com/meta-llama/llama-stack/pull/1659
- https://github.com/meta-llama/llama-stack/pull/1660

**Client SDK**
- https://github.com/meta-llama/llama-stack-client-python/pull/203

**CI**
- 1391130488
<img width="1042" alt="image"
src="https://github.com/user-attachments/assets/69636067-376d-436b-9204-896e2dd490ca"
/>
-- the test_rag_agent_with_attachments is flaky and not related to this
PR

## Doc
<img width="789" alt="image"
src="https://github.com/user-attachments/assets/b88390f3-73d6-4483-b09a-a192064e32d9"
/>


## Client Usage
```python
client.datasets.register(
    source={
        "type": "uri",
        "uri": "lsfs://mydata.jsonl",
    },
    schema="jsonl_messages",
    # optional 
    dataset_id="my_first_train_data"
)

# quick prototype debugging
client.datasets.register(
    data_reference={
        "type": "rows",
        "rows": [
                "messages": [...],
        ],
    },
    schema="jsonl_messages",
)
```

## Test Plan
- CI:
1387805545

```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/datasets/test_datasets.py
```

```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/scoring/test_scoring.py
```

```
pytest -v -s --nbval-lax ./docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
```
 2025-03-17 16:55:45 -07:00
Xi Yan
bcb13c492f
test: revamp eval related integration tests (#1433) 
# What does this PR do?
- revamp and clean up datasets/scoring/eval integration tests
- closes https://github.com/meta-llama/llama-stack/issues/1396

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
**dataset**
```
LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -v tests/integration/datasetio/
```
<img width="842" alt="image"
src="https://github.com/user-attachments/assets/88fc2b6a-b496-47bf-bc0c-8fea48ba36ff"
/>

**scoring**
```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/scoring --text-model meta-llama/Llama-3.1-8B-Instruct --judge-model meta-llama/Llama-3.1-8B-Instruct
```
<img width="851" alt="image"
src="https://github.com/user-attachments/assets/50f46415-b44c-4c37-a6c3-076f2767adb3"
/>


**eval**
```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/eval --text-model meta-llama/Llama-3.1-8B-Instruct --judge-model meta-llama/Llama-3.1-8B-Instruct
```
<img width="841" alt="image"
src="https://github.com/user-attachments/assets/8eb1c65c-3b39-4d66-8ff4-f471ca783e49"
/>


[//]: # (## Documentation)
 2025-03-06 10:51:35 -08:00
Ashwin Bharambe
abfbaf3c1b
refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401) 
All of the tests from `llama_stack/providers/tests/` are now moved to
`tests/integration`.

I converted the `tools`, `scoring` and `datasetio` tests to use API.
However, `eval` and `post_training` proved to be a bit challenging to
leaving those. I think `post_training` should be relatively
straightforward also.

As part of this, I noticed that `wolfram_alpha` tool wasn't added to
some of our commonly used distros so I added it. I am going to remove a
lot of code duplication from distros next so while this looks like a
one-off right now, it will go away and be there uniformly for all
distros.
 2025-03-04 14:53:47 -08:00