Allow AsyncLLMEngine.generate to target a specific DP rank (#19102)

Signed-off-by: Jon Swenson <jmswen@gmail.com>
This commit is contained in:
jmswen
2025-06-04 08:26:47 -07:00
committed by GitHub
parent 8f4ffbd373
commit c8dcc15921
10 changed files with 97 additions and 5 deletions

View File

@@ -42,6 +42,7 @@ def make_request() -> EngineCoreRequest:
arrival_time=time.time(),
lora_request=None,
cache_salt=None,
data_parallel_rank=None,
)