[FEATURE SUPPORT] add gemm pytorch kernel

README.md

@@ -24,7 +24,7 @@ The following common BLAS kernels have been implemented in multiple frameworks.
 | [dot](./docs/dot.md) | dot product | $z = x^\top y$ | $2n$ | $2n$ | [✅](./kernel_course/python_ops/dot.py) | [✅](./kernel_course/pytorch_ops/dot.py) | [✅](./kernel_course/triton_ops/dot.py) | ❌ | [✅](./tests/test_dot.py) |
 | [gemv](./docs/gemv.md) | general matrix-vector multiply | $y = \alpha A x + \beta y$ | $2mn$ | $mn + n + 2m$ | [✅](./kernel_course/python_ops/gemv.py) | [✅](./kernel_course/pytorch_ops/gemv.py) | [✅](./kernel_course/triton_ops/gemv.py) | ❌ | [✅](./tests/test_gemv.py) |
 | [geru](./docs/geru.md) | general rank-1 update | $A = A + \alpha x y^\top$ | $2mn$ | $2mn + m + n$ | [✅](./kernel_course/python_ops/geru.py) | [✅](./kernel_course/pytorch_ops/geru.py) | [✅](./kernel_course/triton_ops/geru.py) | ❌ | [✅](./tests/test_geru.py) |
-| [gemm](./docs/gemm.md) | general matrix-matrix multiply | $C = \alpha A B + \beta C$ | $2mnk$ | $mk + nk + 2mn$ | [✅](./kernel_course/python_ops/gemm.py) | ❌ | ❌ | ❌ | ❌ |
+| [gemm](./docs/gemm.md) | general matrix-matrix multiply | $C = \alpha A B + \beta C$ | $2mnk$ | $mk + nk + 2mn$ | [✅](./kernel_course/python_ops/gemm.py) | [✅](./kernel_course/pytorch_ops/gemm.py) | ❌ | ❌ | ❌ |
 
 
 ## Transformer Modules

kernel_course/pytorch_ops/gemm.py

@@ -0,0 +1,28 @@
+import torch
+
+
+def gemm(
+    A: torch.Tensor,
+    B: torch.Tensor,
+    C: torch.Tensor,
+    alpha: float,
+    beta: float,
+) -> torch.Tensor:
+    """
+    Updates tensor `C` by adding the product of matrices `A` and `B`
+    scaled by `alpha`, and `C` scaled by `beta` using PyTorch operations.
+
+    Args:
+        A (torch.Tensor): First matrix tensor.
+        B (torch.Tensor): Second matrix tensor to be multiplied with `A`.
+        C (torch.Tensor): Matrix tensor to be updated.
+        alpha (float): Scaling factor for the product of `A` and `B`.
+        beta (float): Scaling factor for `C`.
+
+    Returns:
+        torch.Tensor: The updated tensor `C`.
+    """
+
+    C = torch.add(torch.mul(alpha, torch.matmul(A, B)), torch.mul(beta, C))
+
+    return C