[ROCm][CI] Move Spec Decode Speculators + MTP to MI355 (#62053)

Signed-off-by: Djordje Ramic <djoramic@amd.com>

.buildkite/test-amd.yaml

@@ -399,27 +399,6 @@ steps:
   commands:
   - pytest -v -s v1/e2e/spec_decode/draft_model/
 
-- label: ":amd: (MI250) Spec Decode Speculators + MTP" # TBD
-  timeout_in_minutes: 75
-  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250]
-  dind: false
-  agent_pool: mi250_1
-  optional: true
-  working_dir: "/vllm-workspace/tests"
-  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/
-  - vllm/transformers_utils/configs/speculators/
-  - tests/v1/e2e/spec_decode/
-  - vllm/platforms/rocm.py
-  - vllm/v1/attention/backends/
-  commands:
-  - pytest -v -s v1/e2e/spec_decode/speculators/
-  - pytest -v -s v1/e2e/spec_decode/mtp/
-
 #-------------------------------------------------------------  mi250 · misc  ------------------------------------------------------------#
 
 - label: ":amd: (MI300) Python-only Installation" # TBD
@@ -2378,27 +2357,6 @@ steps:
   - VLLM_TP_SIZE=4 VLLM_NEEDLE_TRIALS=2 pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k TRITON_ATTN
   - VLLM_TEST_MODEL=allenai/OLMoE-1B-7B-0924 VLLM_TEST_SERVER_ARGS="--data-parallel-size 4 --enable-expert-parallel --max-model-len 4096" pytest -v -s v1/determinism/test_online_batch_invariance.py
 
-- label: ":amd: (MI300) Spec Decode Speculators + MTP" # TBD
-  timeout_in_minutes: 75
-  mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
-  dind: false
-  agent_pool: mi300_1
-  optional: true
-  working_dir: "/vllm-workspace/tests"
-  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/
-  - vllm/transformers_utils/configs/speculators/
-  - tests/v1/e2e/spec_decode/
-  - vllm/platforms/rocm.py
-  - vllm/v1/attention/backends/
-  commands:
-    - pytest -v -s v1/e2e/spec_decode/speculators/
-    - pytest -v -s v1/e2e/spec_decode/mtp/
-
 - label: ":amd: (MI300) Spec Decode DeepSeek MTP Parallel Load"
   timeout_in_minutes: 45
   mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
@@ -5396,6 +5354,27 @@ steps:
   commands:
   - pytest -v -s v1/e2e/spec_decode/draft_model/
 
+- label: ":amd: (MI355 DPX) Spec Decode Speculators + MTP" # TBD
+  timeout_in_minutes: 75
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
+  dind: false
+  agent_pool: mi355_dpx
+  optional: true
+  working_dir: "/vllm-workspace/tests"
+  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/
+  - vllm/transformers_utils/configs/speculators/
+  - tests/v1/e2e/spec_decode/
+  - vllm/platforms/rocm.py
+  - vllm/v1/attention/backends/
+  commands:
+  - pytest -v -s v1/e2e/spec_decode/speculators/
+  - pytest -v -s v1/e2e/spec_decode/mtp/
+
 - label: ":amd: (MI355 DPX) Spec Decode Eagle 1: DeepSeek + Qwen"
   timeout_in_minutes: 60
   mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]