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 11, 21:15 UTC
[TPU] Bump tpu-inference to 0.12.0 (#30221)
Signed-off-by: Johnny Yang <johnnyyang@google.com>
Johnny Yang committed
Dec 8, 2025 at 12:10 UTC
d1b5e7afbf8a4ff45904c191748594167dd34e78
1 file changed
+1
-2
requirements/tpu.txt
+1
-2
@@ -11,5 +11,4 @@ ray[default]
11
ray[data]
12
setuptools==78.1.0
13
nixl==0.3.0
14
-tpu_info==0.4.0
15
-tpu-inference==0.11.1
14
+tpu-inference==0.12.0