xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-23 20:54:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Fix import (#20233)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-06-29 20:34:54 -07:00 committed by GitHub
parent 5a52f389dd
commit 19108ef311
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/v1/worker/gpu_model_runner.py
View File

@ -45,7 +45,7 @@ from vllm.sequence import IntermediateTensors
from vllm.utils import (STR_DTYPE_TO_TORCH_DTYPE, DeviceMemoryProfiler,
GiB_bytes, LazyLoader, async_tensor_h2d, cdiv,
check_use_alibi, get_dtype_size,
is_pin_memory_available)
is_pin_memory_available, round_up)
from vllm.v1.attention.backends.mamba_attn import Mamba2AttentionBackend
from vllm.v1.attention.backends.utils import (AttentionMetadataBuilder,
CommonAttentionMetadata)
@ -1308,7 +1308,6 @@ class GPUModelRunner(LoRAModelRunnerMixin):
tp_size = self.vllm_config.parallel_config.tensor_parallel_size
if self.compilation_config.pass_config. \
enable_sequence_parallelism and tp_size > 1:
from vllm.utils import round_up
num_input_tokens = round_up(num_scheduled_tokens, tp_size)
else:
num_input_tokens = num_scheduled_tokens