xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-21 02:47:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

more cleanup

Browse Source 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
This commit is contained in:
Sage Moore 2025-07-03 16:35:52 +00:00
parent f7b6e600b8
commit 510e839429
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

@ -1553,6 +1553,8 @@ class GPUModelRunner(LoRAModelRunnerMixin):
def model_inputs(tokens_slice: slice, use_dummy_input: bool) -> tuple:
if use_dummy_input:
logger.info(f"NUM DUMMY TOKENS: {num_dummy_tokens} token slize: {tokens_slice}")
assert num_dummy_tokens == tokens_slice.stop - tokens_slice.start
return self._get_dummy_model_inputs(num_dummy_tokens)
else:
assert scheduler_output is not None