[Bug] Fix Batched DeepGEMM (#47884)
Signed-off-by: Robert Shaw <robertgshaw2-redhat@dgx-b200-02.mgmt.accl-001.lab.rdu2.dc.redhat.com> Co-authored-by: Robert Shaw <robertgshaw2-redhat@dgx-b200-02.mgmt.accl-001.lab.rdu2.dc.redhat.com> Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
co-authored by
Robert Shaw
Claude
parent
9f2b3b093c
commit
572b25b03e
@@ -210,7 +210,7 @@ def persistent_masked_m_silu_mul_quant(
|
||||
DeepGemmQuantScaleFMT.UE8M0,
|
||||
]
|
||||
|
||||
device_capability = current_platform.get_device_capability(device_id=y.device.index)
|
||||
device_capability = current_platform.get_device_capability()
|
||||
assert device_capability is not None
|
||||
cuda_arch = device_capability.to_int()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user