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 12, 12:15 UTC
Fix tpu-inference platform path (#29554)
Signed-off-by: Johnny Yang <johnnyyang@google.com>
Johnny Yang committed
Nov 26, 2025 at 23:25 UTC
3ecabd06eee69e60c2239a6ca7159b978b26d6ce
1 file changed
+1
-1
vllm/platforms/tpu.py
+1
-1
@@ -267,7 +267,7 @@ class TpuPlatform(Platform):
267
268
269
try:
270
- from tpu_inference.platforms.tpu_platforms import (
270
+ from tpu_inference.platforms import (
271
TpuPlatform as TpuInferencePlatform,
272
)
273