[Kernel] DeepEP dispatch-combine kernel integration (#18434)
Signed-off-by: Varun <vsundarr@redhat.com> Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
This commit is contained in:
co-authored by
Varun Sundar Rabindranath
parent
01eee40536
commit
fa98d77773
@@ -18,8 +18,8 @@ def _resize_cache(x: torch.Tensor, v: tuple[int, ...]) -> torch.Tensor:
|
||||
Shrink the given tensor and apply the given view to it. This is
|
||||
used to resize the intermediate fused_moe caches.
|
||||
"""
|
||||
assert prod(
|
||||
v) <= x.numel(), f"{prod(v)} <= {x.numel()}" # CUDAGRAPH unfriendly?
|
||||
assert prod(v) <= x.numel(
|
||||
), f"{v} ({prod(v)}) <= {x.shape} ({x.numel()})" # CUDAGRAPH unfriendly?
|
||||
return x.flatten()[:prod(v)].view(*v)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user