[ROCm][Model][Bugfix] Enable GLM-5.2-MXFP4 on the deepseek_v32 path and fix sparse attention correctness (#51915)
Signed-off-by: Jack Hu <Jack.Hu@amd.com> Signed-off-by: Jack Hu <jack.hu@amd.com> Signed-off-by: Douglas Lehr <Doug.Lehr@amd.com> Co-authored-by: James E T Smith <jamesETsmith@users.noreply.github.com> Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com> Co-authored-by: Douglas Lehr <Doug.Lehr@amd.com>
This commit is contained in:
co-authored by
James E T Smith
Douglas Lehr
Douglas Lehr
parent
9646f53064
commit
1c0eee919d
@@ -665,6 +665,11 @@ class DeepseekV32IndexerCache(torch.nn.Module, AttentionLayerBase):
|
||||
|
||||
def forward(self): ...
|
||||
|
||||
@property
|
||||
def uses_shuffled_layout(self) -> bool:
|
||||
"""Whether this cache's reader expects the shuffled value layout."""
|
||||
return False
|
||||
|
||||
def get_attn_backend(self) -> type[AttentionBackend]:
|
||||
return DeepseekV32IndexerBackend
|
||||
|
||||
|
||||
Reference in New Issue
Block a user