Skip to content

Add EAGLE-3 and LoRA tests for GPT-OSS #2932

Closed
ksuma2109 wants to merge 3 commits intomasterfrom
sk-vllm-vuln
Closed

Add EAGLE-3 and LoRA tests for GPT-OSS #2932
ksuma2109 wants to merge 3 commits intomasterfrom
sk-vllm-vuln

Conversation

@ksuma2109
Copy link
Contributor

Description

Brief description of what this PR is about

  • If this change is a backward incompatible change, why must this change be made?
  • Interesting edge cases to note here

Type of change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • New feature (non-breaking change which adds functionality)
  • This change requires a documentation update

Checklist:

Feature/Issue validation/testing

Please describe the Unit or Integration tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.

  • Test A
    Logs for Test A

  • Test B
    Logs for Test B

@ksuma2109 ksuma2109 requested review from a team and zachgk as code owners October 31, 2025 16:45
@ksuma2109 ksuma2109 changed the title Add Eagle and LoRA tests for GPT-OSS Add EAGLE-3 and LoRA tests for GPT-OSS Oct 31, 2025
)
options = vllm_model_list[model]
options["engine"] = "Python"
options["option.rolling_batch"] = "vllm"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why use the sync vllm?

@pytest.mark.gpu_4
class TestGPTOSS:

def test_lora_llama3_8b(self):
Copy link
Contributor

@xyang16 xyang16 Oct 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not gpt-oss model

r.launch()
client.run("vllm_adapters phi2-unmerged-lora".split())

def test_llama_68m_speculative_eagle(self):
Copy link
Contributor

@xyang16 xyang16 Oct 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not gpt-oss model

@pytest.mark.gpt_oss
@pytest.mark.lora
@pytest.mark.gpu_4
class TestGPTOSS:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We can test this gpt-oss model https://huggingface.co/openai/gpt-oss-20b

@ksuma2109
Copy link
Contributor Author

Closing this as I created a PR on wrong branch. @xyang16 The other branch has the relevant changes.

@ksuma2109 ksuma2109 closed this Oct 31, 2025
@ksuma2109 ksuma2109 deleted the sk-vllm-vuln branch January 31, 2026 01:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants