Float8Tensor per row quantization pass bias to fbgemm kernel

Summary:
Previously bias is not passed to fbgemm kernel for float8 per row quant,
this PR adds it.

Difference is we should have a faster float8 per row quantized kernel, without changing
numerics or other things.

Test Plan:
```
python test/dtypes/test_affine_quantized_float.py -k test_expected_kernels_on_gpu
python test/quantization/quantize_/workflows/float8/test_float8_tensor.py
```

Reviewers:

Subscribers:

Tasks:

Tags:

stack-info: PR: #2884, branch: jerryzh168/stack/60

Author: jerryzh168

test/quantization/quantize_/workflows/float8/test_float8_tensor.py

@@ -415,6 +415,7 @@ def test_moe_weight_reshape_ops(self):
 
     def test_expected_gpu_kernel_fbgemm(self):
         """Making sure KernelPreference.FBGEMM calls correct quantize and gemm kernels
+        and the bias add happens in the gemm kernel for per row quantization
         """
         torch.compiler.reset()
 
@@ -432,9 +433,13 @@ def test_expected_gpu_kernel_fbgemm(self):
         out, code = run_and_get_code(m, x)
 
         # check at least one occurrence of the quantize op and rowwise gemm op
+        # check that there is no `triton_poi_fused_add_0` since the bias add should
+        # happen in the `f8f8bf16_rowwise.default` op instead of separately
         FileCheck().check_count(
             "torch.ops.triton.quantize_fp8_row.default", 1
-        ).check_count("torch.ops.fbgemm.f8f8bf16_rowwise.default", 1).run(code[0])
+        ).check_count("torch.ops.fbgemm.f8f8bf16_rowwise.default", 1).check_not(
+            "triton_poi_fused_add_0"
+        ).run(code[0])
 
 
 common_utils.instantiate_parametrized_tests(TestFloat8Tensor)

torchao/quantization/quantize_/workflows/float8/float8_tensor.py

@@ -296,6 +296,8 @@ def _(func, types, args, kwargs):
                 "Expected fbgemm_gpu_genai package to be installed"
             )
             assert is_sm_at_least_90(), "Expected SM90+ for fbgemm_gpu_genai"
+            mm_config = weight_tensor.mm_config
+            assert mm_config is not None
 
             out_shape = get_out_shape(input_tensor.shape, weight_tensor.shape)
             xq = input_tensor.qdata.reshape(-1, input_tensor.qdata.shape[-1])
@@ -311,6 +313,8 @@ def _(func, types, args, kwargs):
                     wq,
                     x_scale,
                     w_scale,
+                    bias=bias,
+                    use_fast_accum=mm_config.use_fast_accum,
                 ).reshape(out_shape)
             else:
                 assert _is_tensorwise_scaled(weight_tensor)
@@ -319,9 +323,10 @@ def _(func, types, args, kwargs):
                     xq,
                     wq,
                     x_scale * w_scale,
+                    use_fast_accum=mm_config.use_fast_accum,
                 ).reshape(out_shape)
-            if bias is not None:
-                res = res + bias
+                if bias is not None:
+                    res = res + bias
             return res
         else:
             assert kernel_choice == "torch"