A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 11:00 UTC
[Chore] Remove unused method (#18024)
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Robert Shaw committed
May 12, 2025 at 16:59 UTC
195adb47c0f181d32856aed49fad9973c3013217
1 file changed
-5
vllm/v1/core/kv_cache_manager.py
-5
@@ -376,8 +376,3 @@ class KVCacheManager:
376
block.block_id
377
for block in self.single_type_manager.req_to_blocks[request_id]
378
]
379
-
380
- def get_num_blocks(self, request_id: str):
381
- """Get the number of blocks."""
382
- assert request_id in self.single_type_manager.req_to_blocks
383
- return len(self.single_type_manager.req_to_blocks[request_id])