[Model Runner v2] Oracle for model runner v2 - qwen3 dense model by default [1/N] (#39337)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
Wentao Ye
2026-05-14 10:02:33 -07:00
committed by GitHub
co-authored by Nick Hill
parent f3d5360591
commit ae4f59f0ec
6 changed files with 208 additions and 20 deletions
+1 -1
View File
@@ -153,7 +153,7 @@ class Worker(WorkerBase):
if self.profiler_config.profiler not in ("torch", "cuda", None):
raise ValueError(f"Unknown profiler type: {self.profiler_config.profiler}")
self.use_v2_model_runner = envs.VLLM_USE_V2_MODEL_RUNNER
self.use_v2_model_runner = vllm_config.use_v2_model_runner
# pending non-blocking PP send work from the previous iteration
self._pp_send_work: list[Handle] = []