We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent dce78b8 commit 98d234aCopy full SHA for 98d234a
vllm_ascend/worker/worker_v1.py
@@ -181,7 +181,8 @@ def determine_available_memory(self) -> int:
181
peak_memory = torch_npu.npu.memory_stats()["allocated_bytes.all.peak"] + \
182
chuked_prefill_work_space_size
183
else:
184
- peak_memory = torch_npu.npu.memory_stats()["allocated_bytes.all.peak"]
+ peak_memory = torch_npu.npu.memory_stats(
185
+ )["allocated_bytes.all.peak"]
186
# TODO: don`t need impl this func after empty_cache in
187
# Worker.determine_num_available_blocks() unified`
188
NPUPlatform.empty_cache()
0 commit comments