mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-23 21:04:29 +00:00
# What does this PR do? ## Test Plan pytest verifications/openai/test_chat_completion.py --provider together
88 lines
3.2 KiB
Markdown
88 lines
3.2 KiB
Markdown
# Test Results Report
|
|
|
|
*Generated on: 2025-04-08 21:14:02*
|
|
|
|
*This report was generated by running `python tests/verifications/generate_report.py`*
|
|
|
|
## Legend
|
|
|
|
- ✅ - Test passed
|
|
- ❌ - Test failed
|
|
- ⚪ - Test not applicable or not run for this model
|
|
|
|
|
|
## Summary
|
|
|
|
| Provider | Pass Rate | Tests Passed | Total Tests |
|
|
| --- | --- | --- | --- |
|
|
| Together | 67.7% | 21 | 31 |
|
|
| Fireworks | 90.3% | 28 | 31 |
|
|
| Openai | 100.0% | 22 | 22 |
|
|
|
|
|
|
|
|
## Together
|
|
|
|
*Tests run on: 2025-04-08 16:19:59*
|
|
|
|
```bash
|
|
pytest tests/verifications/openai/test_chat_completion.py --provider=together -v
|
|
```
|
|
|
|
| Test | Llama-3.3-70B-Instruct | Llama-4-Maverick-17B-128E-Instruct | Llama-4-Scout-17B-16E-Instruct |
|
|
| --- | --- | --- | --- |
|
|
| test_chat_non_streaming_basic (case 0) | ✅ | ✅ | ✅ |
|
|
| test_chat_non_streaming_basic (case 1) | ✅ | ✅ | ✅ |
|
|
| test_chat_non_streaming_image (case 0) | ⚪ | ✅ | ✅ |
|
|
| test_chat_non_streaming_structured_output (case 0) | ✅ | ✅ | ✅ |
|
|
| test_chat_non_streaming_structured_output (case 1) | ✅ | ✅ | ✅ |
|
|
| test_chat_non_streaming_tool_calling (case 0) | ✅ | ✅ | ✅ |
|
|
| test_chat_streaming_basic (case 0) | ✅ | ❌ | ❌ |
|
|
| test_chat_streaming_basic (case 1) | ✅ | ❌ | ❌ |
|
|
| test_chat_streaming_image (case 0) | ⚪ | ❌ | ❌ |
|
|
| test_chat_streaming_structured_output (case 0) | ✅ | ❌ | ❌ |
|
|
| test_chat_streaming_structured_output (case 1) | ✅ | ❌ | ❌ |
|
|
|
|
## Fireworks
|
|
|
|
*Tests run on: 2025-04-08 16:18:28*
|
|
|
|
```bash
|
|
pytest tests/verifications/openai/test_chat_completion.py --provider=fireworks -v
|
|
```
|
|
|
|
| Test | Llama-3.3-70B-Instruct | Llama-4-Maverick-17B-128E-Instruct | Llama-4-Scout-17B-16E-Instruct |
|
|
| --- | --- | --- | --- |
|
|
| test_chat_non_streaming_basic (case 0) | ✅ | ✅ | ✅ |
|
|
| test_chat_non_streaming_basic (case 1) | ✅ | ✅ | ✅ |
|
|
| test_chat_non_streaming_image (case 0) | ⚪ | ✅ | ✅ |
|
|
| test_chat_non_streaming_structured_output (case 0) | ✅ | ✅ | ✅ |
|
|
| test_chat_non_streaming_structured_output (case 1) | ✅ | ✅ | ✅ |
|
|
| test_chat_non_streaming_tool_calling (case 0) | ✅ | ❌ | ❌ |
|
|
| test_chat_streaming_basic (case 0) | ✅ | ✅ | ✅ |
|
|
| test_chat_streaming_basic (case 1) | ✅ | ✅ | ✅ |
|
|
| test_chat_streaming_image (case 0) | ⚪ | ✅ | ✅ |
|
|
| test_chat_streaming_structured_output (case 0) | ✅ | ✅ | ✅ |
|
|
| test_chat_streaming_structured_output (case 1) | ❌ | ✅ | ✅ |
|
|
|
|
## Openai
|
|
|
|
*Tests run on: 2025-04-08 16:22:02*
|
|
|
|
```bash
|
|
pytest tests/verifications/openai/test_chat_completion.py --provider=openai -v
|
|
```
|
|
|
|
| Test | gpt-4o | gpt-4o-mini |
|
|
| --- | --- | --- |
|
|
| test_chat_non_streaming_basic (case 0) | ✅ | ✅ |
|
|
| test_chat_non_streaming_basic (case 1) | ✅ | ✅ |
|
|
| test_chat_non_streaming_image (case 0) | ✅ | ✅ |
|
|
| test_chat_non_streaming_structured_output (case 0) | ✅ | ✅ |
|
|
| test_chat_non_streaming_structured_output (case 1) | ✅ | ✅ |
|
|
| test_chat_non_streaming_tool_calling (case 0) | ✅ | ✅ |
|
|
| test_chat_streaming_basic (case 0) | ✅ | ✅ |
|
|
| test_chat_streaming_basic (case 1) | ✅ | ✅ |
|
|
| test_chat_streaming_image (case 0) | ✅ | ✅ |
|
|
| test_chat_streaming_structured_output (case 0) | ✅ | ✅ |
|
|
| test_chat_streaming_structured_output (case 1) | ✅ | ✅ |
|