Enable use_batch_forward Optimization on Battlemage GPU (#12516)

* Update get_xpu_device_type() to support bmg

* enable use_batch_forward for bmg

* Update low_bit_linear.py

* Update utils.py

* use batch kernel for fp8e5

python/llm/src/ipex_llm/transformers/low_bit_linear.py

@@ -405,6 +405,7 @@ def use_batch_forward(x: torch.Tensor, qtype: int, output_len: int):
             or (device in ["arc", "flex"] and qtype in [SYM_INT8, FP4])
             or (device in ["arc", "flex", "mtl"] and qtype in [FP8E4])
             or (device in ["lnl"] and qtype in [SYM_INT4] and x.shape[1] % 512 == 0)
+            or (device in ["bmg"] and qtype in [SYM_INT4, FP8E5])
         )
     return False
 

python/llm/src/ipex_llm/transformers/utils.py

@@ -174,6 +174,8 @@ def get_xpu_device_type(x):
     name = torch.xpu.get_device_name(x.device.index)
     if name.startswith("Intel(R) Arc(TM) A"):
         return "arc"
+    elif name.startswith("Intel(R) Graphics [0xe20b]"):
+        return "bmg"
     elif name.startswith("Intel(R) Arc(TM)"):
         if 'V' in name:
             return "lnl"