Add caching mechanism for completed AV blocks in streaming model. Introduce CompletedBlockPieceCache class to manage reusable blocks during strict-window replay, enhancing efficiency. Update profiling hooks for cache operations and refine README documentation to reflect changes in block handling and replay strategies.

profile_streaming_bottleneck_gpu7.py

@@ -231,6 +231,16 @@ def _install_profiling_hooks() -> None:
         "_cache_from_intervals",
         "rolling_cache_rebuild",
     )
+    _patch_function(
+        core.CompletedBlockPieceCache,
+        "put",
+        "completed_block_cache_store",
+    )
+    _patch_function(
+        core.CompletedBlockPieceCache,
+        "get_many",
+        "completed_block_cache_lookup",
+    )
     _patch_function(torch, "save", "output_save")
 
     original_extract = core.OpenStreamReplayExtractor.extract
@@ -423,7 +433,7 @@ def _print_summary(
     bottleneck = max(totals, key=totals.get)
     advice = {
         "media_frames": "bulk-decode/cache the selected 2-FPS resized frames",
-        "processor": "cache processor-ready AV tensors for every causal prefix",
+        "processor": "prefetch or microbatch the ten causal prefixes per 2-s block",
         "audio_tower": "microbatch the ten 0.2-s prefixes in each 2-s block",
         "video_tower": "cache unique 2-FPS visual inputs and batch equal shapes",
         "tmrope": "cache position IDs for the ten repeated prefix shapes",