 AlpinDale
|
a985143768
core: add cuda graph support for encoder-decoder models (#1051)
|
2 hete |
|
AlpinDale
|
960dee2f97
torch.compile: fix functionalization (#1045)
|
2 hete |
|
AlpinDale
|
9797d38b24
torch.compile: allow adding custom compile backends via plugins (#1041)
|
2 hete |
|
AlpinDale
|
304e1e5a8a
core: dump model runner inputs during crash (#1023)
|
2 hete |
|
AlpinDale
|
a113309876
kernel: add meta functions for ops to prevent graph breaks (#1019)
|
2 hete |
|
AlpinDale
|
411ac4f405
vlm: add support for Qwen2-VL model (#1015)
|
2 hete |
|
AlpinDale
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
2 hete |
