[Core] Refactor Worker and ModelRunner to consolidate control plane communication (#5408)
Signed-off-by: Stephanie Wang <swang@cs.berkeley.edu> Signed-off-by: Stephanie <swang@anyscale.com> Co-authored-by: Stephanie <swang@anyscale.com>
This commit is contained in:
co-authored by
Stephanie
parent
82079729cc
commit
dda4811591
@@ -55,8 +55,7 @@ class NeuronExecutor(ExecutorBase):
|
||||
assert execute_model_req.num_lookahead_slots == 0, (
|
||||
"lookahead not supported for Neuron backend.")
|
||||
|
||||
output = self.driver_worker.execute_model(
|
||||
execute_model_req.seq_group_metadata_list)
|
||||
output = self.driver_worker.execute_model(execute_model_req)
|
||||
return output
|
||||
|
||||
def add_lora(self, lora_request: LoRARequest) -> bool:
|
||||
|
||||
Reference in New Issue
Block a user