[xpu] support mtp for xpu(mix) (#5274)

* [XPU] support kernel for mtp(base)

* [XPU] support kernel for mtp(base)

* format

* format

* format

* fix gather next token

* fix step && add test

* fix

* mv pre/post process

* add adjust batch / gather next token for mtp

* fix code style

* fix mtp kenrel name

* fix mtp kernel test

* mv xpu pre/post process

* mv xpu pre/post process

* [xpu] support mtp

* fix code style

fastdeploy/model_executor/layers/sample/ops/apply_penalty_multi_scores.py

@@ -182,24 +182,28 @@ def apply_speculative_penalty_multi_scores(
         from fastdeploy.model_executor.ops.gpu import (
             speculate_get_token_penalty_multi_scores,
         )
-
-        speculate_get_token_penalty_multi_scores(
-            pre_token_ids,
-            logits,
-            repetition_penalties,
-            frequency_penalties,
-            presence_penalties,
-            temperature,
-            bad_words_token_ids,
-            step_idx,
-            min_dec_lens,
-            eos_token_ids,
-            seq_lens_this_time,
-            output_padding_offset,
-            output_cum_offsets,
-            max_len,
+    elif current_platform.is_xpu():
+        from fastdeploy.model_executor.ops.xpu import (
+            speculate_get_token_penalty_multi_scores,
         )
+
     else:
         raise NotImplementedError
+    speculate_get_token_penalty_multi_scores(
+        pre_token_ids,
+        logits,
+        repetition_penalties,
+        frequency_penalties,
+        presence_penalties,
+        temperature,
+        bad_words_token_ids,
+        step_idx,
+        min_dec_lens,
+        eos_token_ids,
+        seq_lens_this_time,
+        output_padding_offset,
+        output_cum_offsets,
+        max_len,
+    )
     # inplace
     return logits