xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-17 13:17:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-08-28 12:55:13 -07:00
parent efba25e21a
commit e451045a66
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/worker/gpu_model_runner.py
View File

@ -2270,6 +2270,8 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
bad_words_token_ids={},
logitsprocs=LogitsProcessors(),
token_ids=None,
num_tokens=None,
num_prompt_tokens=None,
)
try:
sampler_output = self.sampler(logits=logits,