Add allreduce test to 2-gpu test

Signed-off-by: Luka Govedič <[email protected]>

Author: ProExpertProg

.buildkite/test-pipeline.yaml

@@ -812,6 +812,10 @@ steps:
   - vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
   - vllm/v1/attention/backends/flashinfer.py
   - vllm/compilation/
+  # can affect pattern matching
+  - vllm/model_executor/layers/layernorm.py
+  - vllm/model_executor/layers/activation.py
+  - vllm/model_executor/layers/quantization/input_quant_fp8.py
   commands:
     - nvidia-smi
     - python3 examples/offline_inference/basic/chat.py
@@ -833,7 +837,6 @@ steps:
     - pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
     - pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
     # Fusion
-    - pytest -v -s tests/compile/test_fusion_all_reduce.py
     - pytest -v -s tests/compile/test_fusion_attn.py::test_attention_quant_pattern
     - pytest -v -s tests/kernels/moe/test_flashinfer.py
     - pytest -v -s tests/compile/test_silu_mul_quant_fusion.py
@@ -1090,7 +1093,7 @@ steps:
   - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large.txt --tp-size=4
 
 ##### H200 test #####
-- label: Distrubted Tests (H200) # optional
+- label: Distributed Tests (H200) # optional
   gpu: h200
   optional: true
   working_dir: "/vllm-workspace/"
@@ -1110,6 +1113,7 @@ steps:
   commands:
     - pytest -v -s tests/distributed/test_context_parallel.py
     - pytest -v -s tests/distributed/test_nccl_symm_mem_allreduce.py
+    - pytest -v -s tests/compile/test_fusion_all_reduce.py
     - pytest -v -s tests/compile/test_fusions_e2e.py::test_tp2_attn_quant_allreduce_rmsnorm
 
 ##### RL Integration Tests #####