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 16, 02:00 UTC
[BugFix] add more `is not None` check in VllmConfig.__post_init__ (#12138)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Chen Zhang committed
Jan 17, 2025 at 13:33 UTC
d1adb9b4032dd430bb28b8e91feb8164c3a1ca9c
1 file changed
+2
-1
vllm/config.py
+2
-1
@@ -3174,7 +3174,8 @@ class VllmConfig:
3174
3175
if self.compilation_config is None:
3176
self.compilation_config = CompilationConfig()
3177
- if envs.VLLM_USE_V1 and not self.model_config.enforce_eager:
3177
+ if envs.VLLM_USE_V1 and self.model_config is not None and \
3178
+ not self.model_config.enforce_eager:
3179
# NOTE(woosuk): Currently, we use inductor because the piecewise
3180
# CUDA graphs do not work properly with the custom CUDA kernels.
3181
# FIXME(woosuk): Disable inductor to reduce the compilation time