From 8a7368e0692fd1e355e85e196b5d3509343ebabf Mon Sep 17 00:00:00 2001 From: Jade Zheng Date: Thu, 17 Apr 2025 08:44:52 +0800 Subject: [PATCH] [Misc] Remove redundant comment (#16703) Signed-off-by: Jade Zheng --- vllm/v1/worker/gpu_model_runner.py | 3 --- 1 file changed, 3 deletions(-) diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py index c3d84ab377388..bfdb0f72251f6 100644 --- a/vllm/v1/worker/gpu_model_runner.py +++ b/vllm/v1/worker/gpu_model_runner.py @@ -540,9 +540,6 @@ class GPUModelRunner(LoRAModelRunnerMixin): # because M (max_model_len) is not necessarily divisible by block_size. block_table_indices = (req_indices * self.max_num_blocks_per_req + positions_np // self.block_size) - # NOTE(woosuk): We use torch.index_select instead of np.take here - # because torch.index_select is much faster than np.take for large - # tensors. block_table_cpu = self.input_batch.block_table.get_cpu_tensor() block_numbers = block_table_cpu.flatten()[block_table_indices].numpy() block_offsets = positions_np % self.block_size