[bugfix] some bugs maybe fail to run (#896)
### What this PR does / why we need it? Solve the bug that the graph mode is the same as p and d, and some other bugs. ### Does this PR introduce _any_ user-facing change? Wouldn't be ### How was this patch tested? Follow the end-to-end test Signed-off-by: ningbenzhe1 <ningbenzhe@huawei.com>
This commit is contained in:
@@ -219,4 +219,4 @@ def prepare_input_kernel(out_ptr: torch.Tensor, cu_query_lens: torch.Tensor,
|
||||
|
||||
global_indices_flat = global_indices[mask]
|
||||
values_flat = values[mask]
|
||||
out_ptr[global_indices_flat] = values_flat
|
||||
out_ptr[global_indices_flat] = values_flat
|
||||
|
||||
@@ -173,7 +173,7 @@ class NPUWorker(WorkerBase):
|
||||
scheduler_output: "SchedulerOutput",
|
||||
) -> Optional[ModelRunnerOutput]:
|
||||
output = self.model_runner.execute_model(scheduler_output)
|
||||
return output if self.rank == 0 else None
|
||||
return output if self.is_driver_worker else None
|
||||
|
||||
def load_model(self) -> None:
|
||||
self.model_runner.load_model()
|
||||
|
||||
Reference in New Issue
Block a user