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 15, 19:45 UTC
Add ray[data] as tpu dependency (#14691)
Signed-off-by: <ricliu@google.com> Signed-off-by: Richard Liu <ricliu@google.com>
Richard Liu committed
Mar 12, 2025 at 20:13 UTC
ab426ec9c04505d311ef222d8609c6eec729248e
1 file changed
+1
requirements/tpu.txt
+1
@@ -9,6 +9,7 @@ setuptools-scm>=8
9
wheel
10
jinja2
11
ray[default]
12
+ray[data]
13
14
# Install torch_xla
15
--pre