[Perf] API-server scaleout with many-to-many server-engine comms (#17546)
This commit is contained in:
@@ -38,7 +38,6 @@ def make_request(request_id,
|
||||
sampling_params=SamplingParams(max_tokens=17,
|
||||
prompt_logprobs=prompt_logprobs),
|
||||
eos_token_id=100,
|
||||
arrival_time=0,
|
||||
lora_request=None,
|
||||
cache_salt=cache_salt,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user