Allow AsyncLLMEngine.generate to target a specific DP rank (#19102)
Signed-off-by: Jon Swenson <jmswen@gmail.com>
This commit is contained in:
@@ -42,6 +42,7 @@ def make_request() -> EngineCoreRequest:
|
||||
arrival_time=time.time(),
|
||||
lora_request=None,
|
||||
cache_salt=None,
|
||||
data_parallel_rank=None,
|
||||
)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user