wassname/vllm
1
0 Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-10-29 13:50:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

[TPU] Support multi-host inference (#7457)

Browse Source
This commit is contained in:
Woosuk Kwon authored and GitHub committed 2024-08-13 16:31:20 -07:00
1 parent 16422ea76f
commit a08df8322e
2 files changed
+11 -4
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/source/getting_started/tpu-installation.rst
+1 -1
View File
@@ -8,7 +8,7 @@ vLLM supports Google Cloud TPUs using PyTorch XLA.
Requirements
------------
* Google Cloud TPU VM (single host)
* Google Cloud TPU VM (single & multi host)
* TPU versions: v5e, v5p, v4
* Python: 3.10