biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Optimization] Make new_block_ids None if empty (#23262)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
This commit is contained in:
Woosuk Kwon
2025-08-20 18:25:56 -07:00
committed by GitHub
parent bbea1cefdd
commit b029de9902
5 changed files with 57 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
vllm/v1/worker/gpu_model_runner.py
View File

@@ -574,11 +574,13 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
# Update the block IDs.
if not resumed_from_preemption:
# Append the new blocks to the existing block IDs.
for block_ids, new_ids in zip(req_state.block_ids,
new_block_ids):
block_ids.extend(new_ids)
if new_block_ids is not None:
# Append the new blocks to the existing block IDs.
for block_ids, new_ids in zip(req_state.block_ids,
new_block_ids):
block_ids.extend(new_ids)
else:
assert new_block_ids is not None
# The request is resumed from preemption.
# Replace the existing block IDs with the new ones.
req_state.block_ids = new_block_ids
@@ -594,7 +596,9 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
# Update the persistent batch.
self.input_batch.num_computed_tokens_cpu[req_index] = (
num_computed_tokens)
self.input_batch.block_table.append_row(new_block_ids, req_index)
if new_block_ids is not None:
self.input_batch.block_table.append_row(
new_block_ids, req_index)
# For the last rank, we don't need to update the token_ids_cpu
# because the sampled tokens are already cached.