[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
@@ -865,6 +865,8 @@ def nvfp4_w4a16_moe_quant_config(
g2_alphas: torch.Tensor,
w1_scale: torch.Tensor,
w2_scale: torch.Tensor,
gemm1_alpha: float | None = None,
gemm1_beta: float | None = None,
gemm1_clamp_limit: float | None = None,
) -> FusedMoEQuantConfig:
"""
@@ -877,6 +879,8 @@ def nvfp4_w4a16_moe_quant_config(
g1_alphas=g1_alphas,
g2_alphas=g2_alphas,
weight_dtype="nvfp4",
gemm1_alpha=gemm1_alpha,
gemm1_beta=gemm1_beta,
gemm1_clamp_limit=gemm1_clamp_limit,
)