[Kernel] Add b12x FP4 MoE backend (#52018)
Signed-off-by: Luke Alonso <lalonso@gmail.com> Signed-off-by: mgoin <mgoin64@gmail.com> Signed-off-by: Misha Goin <mgoin64@gmail.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -52,6 +52,10 @@ def get_b12x_tensor_fp8_linear() -> ModuleType | None:
|
||||
return _get_submodule("b12x.gemm.tensor_fp8_linear")
|
||||
|
||||
|
||||
def get_b12x_fused_moe() -> ModuleType | None:
|
||||
return _get_submodule("b12x.moe.fused_moe")
|
||||
|
||||
|
||||
def b12x_warmup_token_counts(
|
||||
*,
|
||||
max_tokens: int,
|
||||
|
||||
Reference in New Issue
Block a user