Skip to content

test(sampling): remove unnecessary seed when temperature is 0#785

Merged
prashantgupta24 merged 3 commits intomainfrom
fix-sampling-test
Mar 2, 2026
Merged

test(sampling): remove unnecessary seed when temperature is 0#785
prashantgupta24 merged 3 commits intomainfrom
fix-sampling-test

Conversation

@prashantgupta24
Copy link
Copy Markdown
Collaborator

@prashantgupta24 prashantgupta24 commented Mar 2, 2026

Description

Remove unnecessary seed when temperature is 0. Also replace seed with temperature=0 for test_spyre_stop_sequence since they seem to be randomly failing

Checklist

  • I have read the contributing guidelines
  • My code follows the project's code style (run bash format.sh)
  • I have added tests for my changes (if applicable)
  • I have updated the documentation (if applicable)
  • My commits include a Signed-off-by: line (DCO compliance)

…test

Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
@github-actions
Copy link
Copy Markdown

github-actions Bot commented Mar 2, 2026

👋 Hi! Thank you for contributing to vLLM support on Spyre.
Just a reminder: Make sure that your code passes all the linting checks, otherwise your PR won't be able to be merged. To do so, run ./format.sh.
Now you are good to go 🚀.

We also recommend installing prek and configuring it to check your code before every local commit.

@prashantgupta24
Copy link
Copy Markdown
Collaborator Author

bot:test

Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
… which use temp=0

Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
@prashantgupta24 prashantgupta24 changed the title test(sampling): set temperature to 0 for deterministic stop sequence test(sampling): remove unnecessary seed when temperature is 0 Mar 2, 2026
@prashantgupta24
Copy link
Copy Markdown
Collaborator Author

bot:test

1 similar comment
@prashantgupta24
Copy link
Copy Markdown
Collaborator Author

bot:test

Copy link
Copy Markdown
Collaborator

@joerunde joerunde left a comment

Choose a reason for hiding this comment

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

lpgtm!

@prashantgupta24
Copy link
Copy Markdown
Collaborator Author

All sampling param test passed (#446) so going to merge!

tests/e2e/test_sampling_params.py::test_spyre_temperature[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_max_tokens[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_stop_sequence[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_presence_penalty[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_frequency_penalty[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_n_generations[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_top_p[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_top_k[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_logit_bias[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_min_tokens[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_ignore_eos[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_min_p[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_bad_words[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_detokenize[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED
tests/e2e/test_sampling_params.py::test_spyre_logprobs[ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8-sendnn-max_model_len(512)-max_num_seqs(4)-max_num_batched_tokens(128)] PASSED

@prashantgupta24 prashantgupta24 merged commit b7d3784 into main Mar 2, 2026
13 of 22 checks passed
@prashantgupta24 prashantgupta24 deleted the fix-sampling-test branch March 2, 2026 20:25
romitjain pushed a commit to romitjain/vllm-spyre that referenced this pull request Mar 16, 2026
…spyre#785)

## Description

Remove unnecessary seed when temperature is 0. Also replace `seed` with
`temperature=0` for `test_spyre_stop_sequence` since they seem to be
randomly failing

## Checklist

- [x] I have read the [contributing
guidelines](https://blog.vllm.ai/vllm-spyre/contributing/)
- [x] My code follows the project's code style (run `bash format.sh`)
- [ ] I have added tests for my changes (if applicable)
- [ ] I have updated the documentation (if applicable)
- [x] My commits include a `Signed-off-by:` line (DCO compliance)

---------

Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Signed-off-by: romit <romit@ibm.com>
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