[feat] support prefix cache clearing when /clear_load_weight is called (#4008)

* [feat] support clearing prefix cache (cherry-picked from release/2.1)

* [fix] fix ipc suffix, use port instead

* [fix] fix prefix caching not enabled

* [fix] fix key/value_cache_scales indent

* [fix] fix ep group all-reduce

* [fix] fix clear/update lock not working when workers > 1

* [chore] add preemption triggered info log

* [fix] fix code style

* [fix] fix max_num_seqs config

* [fix] do not force enable_prefix_caching=False in dynamic loading

* [fix] fix ci

* Revert "[fix] fix ci"

This reverts commit 0bc6d55cc8.

* [fix] initialize available_gpu_block_num with max_gpu_block_num

* [fix] fix config splitwise_role

* [fix] fix clearing caches synchronization and add more logs

* [chore] print cache_ready_signal in log

* [fix] fix scheduler_config.splitwise_role

* [fix] fix cache_messager cache_ready_signal create=True

* [fix] stop cache messager from launching in mixed deployment

fastdeploy/engine/args_utils.py

@@ -403,6 +403,7 @@ class EngineArgs:
         """
         Post-initialization processing to set default tokenizer if not provided.
         """
+
         if not self.tokenizer:
             self.tokenizer = self.model
         if self.splitwise_role == "decode":
@@ -411,8 +412,8 @@ class EngineArgs:
             self.enable_prefix_caching = False
         if not current_platform.is_cuda():
             self.enable_prefix_caching = False
-        if self.dynamic_load_weight:
-            self.enable_prefix_caching = False
+        # if self.dynamic_load_weight:
+        #     self.enable_prefix_caching = False
         if self.enable_logprob:
             if self.speculative_config is not None:
                 raise NotImplementedError("Logprob does not support speculation_config.")