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 1, 20:00 UTC
Upgrade tpu-inference to v0.21.0 (#44621)
Signed-off-by: StingLin <sting.lin@cienet.com>
Sting Lin committed
Jun 6, 2026 at 00:12 UTC
b593396c7a70ddf31ddbbfaac2007e6c5f4650bd
1 file changed
+1
-1
requirements/tpu.txt
+1
-1
@@ -12,4 +12,4 @@ ray[data]
12
setuptools==78.1.0
13
setuptools-rust>=1.9.0
14
nixl==0.3.0
15
-tpu-inference==0.20.0
15
+tpu-inference==0.21.0