Skip to content

Adding "AMD: Multi-step Tests" to amdproduction. #19508

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Jun 14, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .buildkite/test-pipeline.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -669,7 +669,7 @@ steps:
- pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins

- label: Multi-step Tests (4 GPUs) # 36min
mirror_hardwares: [amdexperimental]
mirror_hardwares: [amdexperimental, amdproduction]
working_dir: "/vllm-workspace/tests"
num_gpus: 4
source_file_dependencies:
Expand Down
10 changes: 10 additions & 0 deletions tests/multi_step/test_correctness_llm.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@

import pytest

from vllm.platforms import current_platform
from vllm.utils import STR_BACKEND_ENV_VAR

from ..models.utils import check_logprobs_close, check_outputs_equal
Expand Down Expand Up @@ -71,6 +72,12 @@ def test_multi_step_llm(
num_logprobs: corresponds to the `logprobs` argument to the OpenAI
completions endpoint; `None` -> 1 logprob returned.
"""
if current_platform.is_rocm() and \
(attention_backend == "FLASHINFER" or enable_chunked_prefill):
pytest.skip(
"Multi-Step with FLASHINFER or Chunked-Prefill is not supported"
"on ROCm")

with monkeypatch.context() as m:
m.setenv(STR_BACKEND_ENV_VAR, attention_backend)

Expand Down Expand Up @@ -221,6 +228,9 @@ def test_multi_step_llm_w_prompt_logprobs(
@pytest.mark.parametrize("num_prompts", NUM_PROMPTS)
@pytest.mark.parametrize("num_logprobs", [None, 5])
@pytest.mark.parametrize("attention_backend", ["FLASH_ATTN"])
@pytest.mark.skipif(
current_platform.is_rocm(),
reason="Multi-Step + Chunked-Prefill not supported on ROCm")
def test_multi_step_llm_chunked_prefill_prefix_cache(
vllm_runner,
example_prompts,
Expand Down