vllm/device_allocator/cumem.py · fdb09c77d6f92fab0ebced332aa79fda86eaf1fc · OpenDAS / vllm_cscc · GitLab

"vscode:/vscode.git/clone" did not exist on "a26e8dc7ff2111a005144d775ecf9cebf56c45b2"

Find file Blame History Permalink

[sleep mode] save memory for on-the-fly quantization (#24731) · fdb09c77
youkaichao authored Sep 12, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
fdb09c77

cumem.py 12.2 KB