A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 12:15 UTC
[Bugfix] Fix lint error (#17547)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
May 2, 2025 at 02:12 UTC
9b1769dd9ad13a5688d1e2b1b5f00b07b3716969
1 file changed
+1
-2
vllm/config.py
+1
-2
@@ -4250,8 +4250,7 @@ class VllmConfig:
4250
elif len(cuda_graph_sizes) > 1:
4251
batch_size_capture_list = sorted(cuda_graph_sizes)
4252
else:
4253
- raise TypeError(
4254
- f"Invalid value for {cuda_graph_sizes=}.")
4253
+ raise TypeError(f"Invalid value for {cuda_graph_sizes=}.")
4254
if self.parallel_config.tensor_parallel_size > 1 and \
4255
self.compilation_config.pass_config.enable_sequence_parallelism:
4256
batch_size_capture_list = \