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 3, 01:45 UTC
Fix the docker build failure in tpu-inference (#43360)
Signed-off-by: mrjunwan-lang <mrjunwan@google.com>
mrjunwan-lang committed
May 22, 2026 at 01:36 UTC
a7616977176e12ddb14c0daab00cd2a2161ba37c
1 file changed
+1
requirements/tpu.txt
+1
@@ -10,5 +10,6 @@ jinja2>=3.1.6
10
ray[default]
11
ray[data]
12
setuptools==78.1.0
13
+setuptools-rust>=1.9.0
14
nixl==0.3.0
15
tpu-inference==0.19.0