Fix CI and install docs (#3821)

python/sglang/srt/managers/scheduler.py

@@ -1455,7 +1455,7 @@ class Scheduler:
             completion_tokens = []
             cached_tokens = []
             spec_verify_ct = []
-            hidden_states = []
+            output_hidden_states = [] if self.server_args.return_hidden_states else None
 
             if return_logprob:
                 input_token_logprobs_val = []
@@ -1522,7 +1522,8 @@ class Scheduler:
                         output_top_logprobs_val.append(req.output_top_logprobs_val)
                         output_top_logprobs_idx.append(req.output_top_logprobs_idx)
 
-                    hidden_states.append(req.hidden_states)
+                    if self.server_args.return_hidden_states:
+                        output_hidden_states.append(req.hidden_states)
 
             # Send to detokenizer
             if rids:
@@ -1550,7 +1551,7 @@ class Scheduler:
                         input_top_logprobs_idx,
                         output_top_logprobs_val,
                         output_top_logprobs_idx,
-                        hidden_states,
+                        output_hidden_states,
                     )
                 )
         else:  # embedding or reward model

python/sglang/srt/managers/tokenizer_manager.py

@@ -796,10 +796,7 @@ class TokenizerManager:
                     }
                 )
 
-            if (
-                hasattr(recv_obj, "output_hidden_states")
-                and len(recv_obj.output_hidden_states[i]) > 0
-            ):
+            if getattr(recv_obj, "output_hidden_states", None):
                 meta_info["hidden_states"] = recv_obj.output_hidden_states[i]
 
             if isinstance(recv_obj, BatchStrOut):