|
inference
|
ca6095c04d
a generic test for every inference engine
|
1 anno fa |
|
networking
|
445eda156c
dynamically assign shards to nodes deterministically weighted by memory
|
1 anno fa |
|
orchestration
|
445eda156c
dynamically assign shards to nodes deterministically weighted by memory
|
1 anno fa |
|
topology
|
36b8456798
collect global topology with local peer visibility, ring memory weighted partitioning strategy
|
1 anno fa |
|
.gitignore
|
850b72d3ea
make StatefulShardedModel callable, add some tests for mlx sharded inference
|
1 anno fa |
|
example_user.py
|
36b8456798
collect global topology with local peer visibility, ring memory weighted partitioning strategy
|
1 anno fa |
|
example_user_2.py
|
445eda156c
dynamically assign shards to nodes deterministically weighted by memory
|
1 anno fa |
|
main.py
|
36b8456798
collect global topology with local peer visibility, ring memory weighted partitioning strategy
|
1 anno fa |
|
main_dynamic.py
|
445eda156c
dynamically assign shards to nodes deterministically weighted by memory
|
1 anno fa |
|
requirements.txt
|
3a66a0a4a8
add requirements.txt
|
1 anno fa |
Alex Cheema
ca6095c04d
a generic test for every inference engine