xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-20 14:50:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Remove redundant comment (#16703)

Browse Source 
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
This commit is contained in:
Jade Zheng 2025-04-17 08:44:52 +08:00 committed by GitHub
parent 93e561ec4d
commit 8a7368e069
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/v1/worker/gpu_model_runner.py
View File

@ -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