[Intel GPU] Add MLA support to Intel XPU Attention backend for Prefill (#35866)

Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
2026-09-08 10:29:28 +08:00
parent 8656901504
commit cf35384fe4
4 changed files with 60 additions and 80 deletions
@@ -72,14 +72,14 @@ class TestIntelXPUBackend(CustomTestCase):
        [
            "--json-model-override-args",
            '{"num_hidden_layers": 4}',
-            "--decode-attention-backend",
+            "--attention-backend",
            "intel_xpu",
            "--moe-runner-backend",
            "triton",  # FP8 is not yet supported in sgl-kernel
        ],
        min_throughput=32,
    )
-    def test_mla_decode_attention_backend(self):
+    def test_mla_models_with_intel_xpu_attention_backend(self):
        return DEFAULT_MODEL_NAME_FOR_TEST_FP8_WITH_MOE