[HiCache & PD]Fixed detailed cache hit breakdown in PD scenarios. (#21764)

python/sglang/srt/disaggregation/decode.py

@@ -959,6 +959,9 @@ class DecodeTransferQueue:
         # Case 3: Success - commit the transfer
         decode_req.req.output_ids.append(output_id[0].item())
         decode_req.req.cached_tokens = cached_tokens[0].item()
+        decode_req.req.cached_tokens_device = cached_tokens[1].item()
+        decode_req.req.cached_tokens_host = cached_tokens[2].item()
+        decode_req.req.cached_tokens_storage = cached_tokens[3].item()
         if not self.spec_algorithm.is_none():
             decode_req.req.output_topk_p = output_topk_p
             decode_req.req.output_topk_index = output_topk_index

python/sglang/srt/disaggregation/utils.py

@@ -251,6 +251,9 @@ class MetadataBuffers:
 
         self.output_ids[req.metadata_buffer_index][0] = req.output_ids[0]
         self.cached_tokens[req.metadata_buffer_index][0] = req.cached_tokens
+        self.cached_tokens[req.metadata_buffer_index][1] = req.cached_tokens_device
+        self.cached_tokens[req.metadata_buffer_index][2] = req.cached_tokens_host
+        self.cached_tokens[req.metadata_buffer_index][3] = req.cached_tokens_storage
         if req.return_logprob:
             if req.output_token_logprobs_val:  # not none or empty list
                 self.output_token_logprobs_val[req.metadata_buffer_index][0] = (

python/sglang/srt/managers/scheduler_output_processor_mixin.py

@@ -55,15 +55,10 @@ class SchedulerOutputProcessorMixin:
         """Get detailed cache breakdown for a request, if available.
 
         Returns:
-            - None if HiCache is not enabled
+            - None if no cached tokens at all
-            - {"device": X, "host": Y} if HiCache enabled but L3 storage is not
+            - {"device": X, "host": Y} without storage breakdown
-            - {"device": X, "host": Y, "storage": Z, "storage_backend": "..."} if L3 enabled
+            - {"device": X, "host": Y, "storage": Z} with storage breakdown
         """
-        # Only show details if HiCache is enabled
-        if not getattr(self, "enable_hierarchical_cache", False):
-            return None
-
-        # Only show if there are any cached tokens
         if (
             req.cached_tokens_device > 0
             or req.cached_tokens_host > 0
@@ -78,6 +73,13 @@ class SchedulerOutputProcessorMixin:
                 details["storage"] = req.cached_tokens_storage
                 details["storage_backend"] = self._get_storage_backend_type()
             return details
+
+        if req.cached_tokens > 0:
+            return {
+                "device": req.cached_tokens,
+                "host": 0,
+            }
+
         return None
 
     def process_batch_result_prebuilt(self: Scheduler, batch: ScheduleBatch):