electriclilies commented on a change in pull request #6351:
URL: https://github.com/apache/incubator-tvm/pull/6351#discussion_r479459655
##########
File path: tests/python/relay/test_op_level10.py
##########
@@ -326,6 +326,23 @@ def verify_batch_matmul(x_shape, y_shape, out_shape,
dtype="float32"):
z = intrp.evaluate(func)(x_np, y_np)
tvm.testing.assert_allclose(z.asnumpy(), z_np, rtol=1e-5)
+def verify_dynamic_batch_matmul(x_shape, y_shape, out_shape, dtype="float32"):
+ x = relay.var("x", relay.TensorType(x_shape, dtype))
+ y = relay.var("y", relay.TensorType((relay.Any(), ) * len(y_shape), dtype))
+ z = relay.nn.batch_matmul(x, y)
+
+ func = relay.Function([x, y], z)
+ x_np = np.random.uniform(size=x_shape).astype(dtype)
+ y_np = np.random.uniform(size=y_shape).astype(dtype)
+ z_np = tvm.topi.testing.batch_matmul(x_np, y_np)
+
+ for target, ctx in ctx_list():
+ for kind in ["vm", "debug"]:
+ mod = tvm.ir.IRModule.from_expr(func)
Review comment:
Looks like you forgot to continue if GPU is the target hardware, which
is causing the current CI failure
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
