[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:
Luke Alonso
2026-08-21 08:04:36 -07:00
committed by GitHub
co-authored by mgoin
parent 5ee84d3c52
commit 2740c817ff
23 changed files with 2417 additions and 60 deletions
+4
View File
@@ -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,