Delete CUTLASS FP8 blockwise for SM90 and SM100, move SM120 to JIT and add SwapAB (#30438)

Co-authored-by: Brayden Zhong <brayden.zhong@radixark.ai>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: root <root@sgl-b300-inference.datacrunch.io>
Co-authored-by: Brayden Zhong <brayden@radixark.ai>

sgl-kernel/python/sgl_kernel/__init__.py

@@ -57,7 +57,6 @@ else:
         awq_dequantize,
         bmm_fp8,
         dsv3_fused_a_gemm,
-        fp8_blockwise_scaled_mm,
         fp8_scaled_mm,
         gptq_gemm,
         gptq_shuffle,
@@ -178,7 +177,6 @@ else:
         "fast_topk_transform_ragged_fused",
         "fast_topk_v2",
         "fp8_blockwise_scaled_grouped_mm",
-        "fp8_blockwise_scaled_mm",
         "fp8_scaled_mm",
         "fused_add_rmsnorm",
         "fused_qk_norm_rope",

sgl-kernel/python/sgl_kernel/gemm.py

@@ -21,16 +21,6 @@ def int8_scaled_mm(mat_a, mat_b, scales_a, scales_b, out_dtype, bias=None):
     )
 
 
-def fp8_blockwise_scaled_mm(mat_a, mat_b, scales_a, scales_b, out_dtype):
-    return torch.ops.sgl_kernel.fp8_blockwise_scaled_mm.default(
-        mat_a,
-        mat_b,
-        scales_a,
-        scales_b,
-        out_dtype,
-    )
-
-
 def fp8_scaled_mm(mat_a, mat_b, scales_a, scales_b, out_dtype, bias=None):
     return torch.ops.sgl_kernel.fp8_scaled_mm.default(
         mat_a,