diff --git a/vllm_spyre/v1/worker/spyre_model_runner.py b/vllm_spyre/v1/worker/spyre_model_runner.py index c376258c6..f537939b3 100644 --- a/vllm_spyre/v1/worker/spyre_model_runner.py +++ b/vllm_spyre/v1/worker/spyre_model_runner.py @@ -1008,7 +1008,7 @@ def _allocate_new_blocks_wrapper(self, req_id: str, num_tokens: int): def _get_blocks(self, request_id: str) -> list[KVCacheBlock]: return self.kv_cache_manager.req_to_blocks[request_id] - def get_total_spyre_blocks(self) -> int: + def get_total_spyre_blocks(self) -> int: """Returns the total number of KV cache blocks available for spyre. This currently returns the number of blocks required for a full-sized batch, which may be greater than the available memory.