optimize infer_auto_device_map for multi-GPU allocation #3321
feat: allow infer_auto_device_map to avoid unnecessary memory reserva…
00dbeffa
Merge branch 'main' into feature/infer-auto-device-map-multi-gpu-allo…
f4de3c0f
Merge remote-tracking branch 'upstream/main' into feature/infer-auto-…
bb22ffc8
fix: let function recompute device_map when it is {}
6a3ff7eb
test: add tests for reserve_max_layer
0af58995
Nech-C
marked this pull request as ready for review 123 days ago
Nech-C
changed the title [WIP] optimize infer_auto_device_map for multi-GPU allocation optimize infer_auto_device_map for multi-GPU allocation 122 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub