xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-08 23:07:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: apply suggestions from @njhill

Browse Source 
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
This commit is contained in:
zhuhaoran 2025-12-06 13:28:08 +08:00
parent 70189d8eb0
commit 0999b7224a
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/v1/worker/gpu_input_batch.py
View File

@ -950,10 +950,9 @@ class InputBatch:
assert self.async_copy_ready_event is not None
self.async_copy_ready_event.synchronize()
sampled_token_ids = self.sampled_token_ids_cpu.tolist()
# Replace placeholder token id with actual sampled id.
req_output_token_ids[-len(sampled_token_ids[prev_index]) :] = (
sampled_token_ids[prev_index]
)
# Replace placeholder token id(s) with actual sampled id(s).
if sampled_ids := sampled_token_ids[prev_index]:
req_output_token_ids[-len(sampled_ids) :] = sampled_ids
@property
def num_reqs(self) -> int: