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

[Bugfix] Fix DP MTP Dummy Run (#35243)

Browse Source 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
This commit is contained in:
Benjamin Chislett
2026-03-17 11:16:48 -04:00
committed by GitHub
parent c9e5096256
commit f63ed7b5ac
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -903,7 +903,8 @@ class Worker(WorkerBase):
self.profiler.stop()
def execute_dummy_batch(self) -> None:
self.model_runner._dummy_run(1, uniform_decode=True)
num_tokens = getattr(self.model_runner, "uniform_decode_query_len", 1)
self.model_runner._dummy_run(num_tokens, uniform_decode=True)
def add_lora(self, lora_request: LoRARequest) -> bool:
return self.model_runner.add_lora(lora_request)