|
inference
|
b01f69bb6b
add support for multiple concurrent requests with request ids
|
hai 1 ano |
|
networking
|
b01f69bb6b
add support for multiple concurrent requests with request ids
|
hai 1 ano |
|
orchestration
|
b01f69bb6b
add support for multiple concurrent requests with request ids
|
hai 1 ano |
|
topology
|
36b8456798
collect global topology with local peer visibility, ring memory weighted partitioning strategy
|
hai 1 ano |
|
.gitignore
|
850b72d3ea
make StatefulShardedModel callable, add some tests for mlx sharded inference
|
hai 1 ano |
|
example_user.py
|
36b8456798
collect global topology with local peer visibility, ring memory weighted partitioning strategy
|
hai 1 ano |
|
example_user_2.py
|
b01f69bb6b
add support for multiple concurrent requests with request ids
|
hai 1 ano |
|
main.py
|
36b8456798
collect global topology with local peer visibility, ring memory weighted partitioning strategy
|
hai 1 ano |
|
main_dynamic.py
|
7077652c8e
graceful node shutdown
|
hai 1 ano |
|
requirements.txt
|
3a66a0a4a8
add requirements.txt
|
hai 1 ano |
Alex Cheema
b01f69bb6b
add support for multiple concurrent requests with request ids