[Perf] Eliminate padding and slicing op for GPT-OSS with Flashinfer MXFP4 MXFP8 MoE (#30647)

Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>

tests/compile/fusions_e2e/conftest.py

@@ -82,6 +82,10 @@ def run_e2e_fusion_test(monkeypatch, caplog_mp_spawn):
                 f"attention backend '{attn_backend.backend.name}'"
             )
 
+        # TODO: remove this after finishing migration from envs to model kwargs
+        if model_name == "openai/gpt-oss-20b":
+            monkeypatch.setenv("VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8", "1")
+
         # Disable, compile cache to make sure custom passes run.
         # Otherwise, we can't verify fusion happened through the logs.
         monkeypatch.setenv("VLLM_DISABLE_COMPILE_CACHE", "1")