Integrate flashinfer b12x MoE and FP4 GEMM kernels for SM120/121 (#40082)
Signed-off-by: Meenakshi Venkataraman <meenakshiv@nvidia.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Sonnet 4.6
parent
f2d5e3d3ae
commit
363fc84407
@@ -317,6 +317,7 @@ def prepare_nvfp4_moe_layer_for_fi_or_cutlass(
|
||||
NvFp4MoeBackend.FLASHINFER_CUTLASS,
|
||||
NvFp4MoeBackend.FLASHINFER_TRTLLM,
|
||||
NvFp4MoeBackend.FLASHINFER_CUTEDSL_BATCHED,
|
||||
NvFp4MoeBackend.FLASHINFER_B12X,
|
||||
]
|
||||
|
||||
# Reorder [w1, w3] to [w3, w1] for FI NVFP4 MoE kernels.
|
||||
@@ -328,6 +329,7 @@ def prepare_nvfp4_moe_layer_for_fi_or_cutlass(
|
||||
in [
|
||||
NvFp4MoeBackend.FLASHINFER_CUTLASS,
|
||||
NvFp4MoeBackend.FLASHINFER_TRTLLM,
|
||||
NvFp4MoeBackend.FLASHINFER_B12X,
|
||||
]
|
||||
):
|
||||
w13, w13_scale = reorder_w1w3_to_w3w1(w13, w13_scale)
|
||||
|
||||
Reference in New Issue
Block a user