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 16, 05:45 UTC
[TPU] Update requirements-tpu (#10726)
Signed-off-by: Richard Liu <ricliu@google.com>
Richard Liu committed
Nov 28, 2024 at 02:30 UTC
3ed5e7314667f0a9c0c47e6d635ac82fd93296a2
1 file changed
+5
-5
requirements-tpu.txt
+5
-5
@@ -16,8 +16,8 @@ ray[default]
16
--find-links https://storage.googleapis.com/libtpu-releases/index.html
17
--find-links https://storage.googleapis.com/jax-releases/jax_nightly_releases.html
18
--find-links https://storage.googleapis.com/jax-releases/jaxlib_nightly_releases.html
19
-torch==2.6.0.dev20241114+cpu
20
-torchvision==0.20.0.dev20241114+cpu
21
-torch_xla[tpu] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.6.0.dev20241114-cp310-cp310-linux_x86_64.whl
22
-jaxlib==0.4.32.dev20240829
23
-jax==0.4.32.dev20240829
19
+torch==2.6.0.dev20241126+cpu
20
+torchvision==0.20.0.dev20241126+cpu
21
+torch_xla[tpu] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.6.0.dev20241126-cp310-cp310-linux_x86_64.whl
22
+jaxlib==0.4.36.dev20241122
23
+jax==0.4.36.dev20241122