diff --git a/fastdeploy/engine/common_engine.py b/fastdeploy/engine/common_engine.py index 51419bde9..5e152f746 100644 --- a/fastdeploy/engine/common_engine.py +++ b/fastdeploy/engine/common_engine.py @@ -701,7 +701,7 @@ class EngineService: tasks = self.scheduler.get_requests( available_blocks=available_blocks, block_size=self.cfg.cache_config.block_size, - reserved_output_blocks=self.cfg.cache_config.enc_dec_block_num, + reserved_output_blocks=0, # self.cfg.cache_config.enc_dec_block_num max_num_batched_tokens=max_num_batched_tokens, batch=num_prefill_batch, )