From a19ff2218a79a99fcd9ebf3a2cf202c9f7eeb9f9 Mon Sep 17 00:00:00 2001 From: Matt <156021403+mawong-amd@users.noreply.github.com> Date: Sun, 21 Jun 2026 17:40:02 -0500 Subject: [PATCH] [Hardware][AMD][CI] Fix Spec Decode Eagle test group (#46018) Signed-off-by: Matthew Wong --- .buildkite/test-amd.yaml | 3 ++- .buildkite/test_areas/spec_decode.yaml | 14 ++++++++++++++ tests/v1/e2e/spec_decode/test_spec_decode.py | 2 +- 3 files changed, 17 insertions(+), 2 deletions(-) diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml index 191537276e..bc0687db3a 100644 --- a/.buildkite/test-amd.yaml +++ b/.buildkite/test-amd.yaml @@ -2122,9 +2122,10 @@ steps: - pytest -v -s v1/e2e/spec_decode -k "draft_model or no_sync or batch_inference" - label: Spec Decode Eagle # TBD - timeout_in_minutes: 180 + timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 + optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/v1/spec_decode/ diff --git a/.buildkite/test_areas/spec_decode.yaml b/.buildkite/test_areas/spec_decode.yaml index bc73a53a35..6e532eddc7 100644 --- a/.buildkite/test_areas/spec_decode.yaml +++ b/.buildkite/test_areas/spec_decode.yaml @@ -12,6 +12,20 @@ steps: - tests/v1/e2e/spec_decode/ commands: - pytest -v -s v1/e2e/spec_decode -k "eagle_correctness" + mirror: + amd: + device: mi325_1 + timeout_in_minutes: 45 + depends_on: + - image-build-amd + source_file_dependencies: + - vllm/v1/spec_decode/ + - vllm/v1/worker/gpu/spec_decode/ + - vllm/model_executor/model_loader/ + - vllm/v1/sample/ + - vllm/model_executor/layers/ + - tests/v1/e2e/spec_decode/ + - vllm/platforms/rocm.py - label: Spec Decode Eagle Nightly B200 key: spec-decode-eagle-nightly-b200 diff --git a/tests/v1/e2e/spec_decode/test_spec_decode.py b/tests/v1/e2e/spec_decode/test_spec_decode.py index 06e8b3bf0e..532a3e8d6a 100644 --- a/tests/v1/e2e/spec_decode/test_spec_decode.py +++ b/tests/v1/e2e/spec_decode/test_spec_decode.py @@ -425,7 +425,7 @@ def _run_eagle_correctness( if "deepseek" in model_setup[1].lower(): m.setenv("VLLM_ROCM_USE_AITER", "1") m.delenv("VLLM_MLA_DISABLE", raising=False) - attention_config = {"backend": "TRITON_MLA"} + attention_config = {"backend": "ROCM_AITER_MLA"} else: m.setenv("VLLM_ROCM_USE_AITER", "1")