[Feature] support pool (#3827)

* support pool

* update pooling

* add pooler_config and check

* update

* support AutoWeightsLoader load weight

* fix

* update

* delete print

* update pre-commit

* fix

* fix xpu

* fix ModelRegistry->model_registry

* fix Copilot review

* fix pooler.py

* delete StepPooler

* fix abstract

* fix default_loader_v1

* fix Pre Commit

* support torch qwen3 dense

* add test and fix torch-qwen

* fix

* fix

* adapter ci:

* fix review

* fix pooling_params.py

* fix

* fix tasks.py 2025

* fix print and logger

* Modefy ModelRegistry and delete AutoWeightsLoader

* fix logger

* fix test_embedding

* fix ci bug

* ernie4_5 model_registry

* fix test

* support Qwen3-Embedding-0.6B tp=1 load

* fix extra code

* fix

* delete fix vocab_size

* delete prepare_params_dict

* fix:

fastdeploy/worker/gpu_model_runner.py

@@ -1319,8 +1319,12 @@ class GPUModelRunner(ModelRunnerBase):
                 self.parallel_config.max_model_len,
             )
 
-            # 4. Execute spec decode
-            logits = self.model.compute_logits(hidden_states)
+            logits = None
+            if hasattr(self.model, "is_pooling_model") and self.model.is_pooling_model:
+                pass
+            else:
+                # 4. Execute spec decode
+                logits = self.model.compute_logits(hidden_states)
 
             if not self.speculative_decoding:
                 set_value_by_flags_and_idx(
@@ -1625,8 +1629,13 @@ class GPUModelRunner(ModelRunnerBase):
             self.parallel_config.max_model_len,
         )
 
+        logits = None
         # 4. Compute logits, Sample
-        logits = self.model.compute_logits(hidden_states)
+        if hasattr(self.model, "is_pooling_model") and self.model.is_pooling_model:
+            pass
+        else:
+            # 4. Execute spec decode
+            logits = self.model.compute_logits(hidden_states)
 
         if not self.speculative_decoding:
             set_value_by_flags_and_idx(