xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 10:57:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Remove unused numpy tensor (#18084)

Browse Source 
Signed-off-by: Roger Wang <hey@rogerw.me>
This commit is contained in:
Roger Wang 2025-05-13 19:33:40 -07:00 committed by GitHub
parent d5af47a149
commit 6e27c6d86b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/v1/worker/gpu_model_runner.py
View File

@ -287,7 +287,6 @@ class GPUModelRunner(LoRAModelRunnerMixin):
dtype=torch.int32, dtype=torch.int32,
device="cpu", device="cpu",
pin_memory=self.pin_memory) pin_memory=self.pin_memory)
self.input_ids_np = self.input_ids_cpu.numpy()
self.positions_cpu = torch.zeros(self.max_num_tokens, self.positions_cpu = torch.zeros(self.max_num_tokens,
dtype=torch.int64, dtype=torch.int64,
device="cpu", device="cpu",

1
vllm/v1/worker/tpu_model_runner.py
View File

@ -191,7 +191,6 @@ class TPUModelRunner(LoRAModelRunnerMixin):
self.input_ids_cpu = torch.zeros(self.max_num_tokens, self.input_ids_cpu = torch.zeros(self.max_num_tokens,
dtype=torch.int32, dtype=torch.int32,
device="cpu") device="cpu")
self.input_ids_np = self.input_ids_cpu.numpy()
self.positions_cpu = torch.zeros(self.max_num_tokens, self.positions_cpu = torch.zeros(self.max_num_tokens,
dtype=torch.int32, dtype=torch.int32,