[Apache TVM Discuss] [Questions] Provide external functions as TVMScript?

I was able to invoke an external function using Relax: ``` import tvm from tvm.script import relax as R from tvm.script import ir as I import numpy as np @tvm.register_func("foo", override=True) def foo(A, out): out = A.numpy() print(out) @I.ir_module class Module: @R.function

[Apache TVM Discuss] [Questions] Provide external functions as TVMScript?

I tried a simple program: ``` import tvm from tvm.ir.module import IRModule from tvm.script import tir as T import numpy as np def foo(A): A[0] = 2.0 @T.prim_func def main(a: T.handle): T.func_attr({"global_symbol": "main", "tir.noalias": True}) A = T.match_buffer(a, (5,), "float32

[Apache TVM Discuss] [Questions] Provide external functions as TVMScript?

I have a simple TVMScript program: ``` import tvm from tvm.ir.module import IRModule from tvm.script import tir as T @T.prim_func def main(A: T.Buffer[(128,), "float32"], B: T.Buffer[(128,), "float32"], C: T.Buffer[(128,), "float32"]): T.func_attr({"global_symbol":

[Apache TVM Discuss] [Questions] Print values in Tensor IR?

Is there a way to print elements in the TensorIR program itself? For eg. I have a simple program like: ``` import tvm from tvm.ir.module import IRModule from tvm.script import tir as T import numpy as np @T.prim_func def main(A: T.Buffer[(128,), "float32"], B: T.Buffer[(128,), "float32

[Apache TVM Discuss] [Questions] `call_tir` initialize `out_sinfo` outside

Simpler example (cant edit the original post): ``` import tvm from tvm.script import relax as R from tvm.script import ir as I from tvm.script import tir as T @I.ir_module class Module: @T.prim_func def dense_loop(CSR_VAL: T.handle, OUT: T.handle): csr_val = T.match_buffer(CSR_

[Apache TVM Discuss] [Questions] Why does meta schedule not find any schedules?

``` import tvm from tvm.script import relax as R from tvm.script import ir as I from tvm.script import tir as T import tempfile import tvm.meta_schedule as ms from tvm.ir import IRModule @I.ir_module class Module: @T.prim_func def dense_loop( VAL: T.handle, VEC: T.handle,

[Apache TVM Discuss] [Questions] Why does meta schedule not find any schedules?

Thanks! What is the difference between using `relax.get_pipeline` with `static_shape_tuning` and `ms.tir_integration.compile_tir`? For the few examples I tried, I get the same generated module. Is the former just a wrapper over the latter? --- [Visit Topic](https://discuss.tvm.apache.or

[Apache TVM Discuss] [Questions] Disable specific schedule in MetaSchedule?

Specifically, is there a way to force MetaSchedule to ignore the parallelize primitive from its search space? --- [Visit Topic](https://discuss.tvm.apache.org/t/disable-specific-schedule-in-metaschedule/18474/1) to respond. You are receiving this because you enabled mailing list mode. T

[Apache TVM Discuss] [Questions] `call_tir` initialize `out_sinfo` outside

``` import tvm from tvm.script import relax as R from tvm.script import ir as I from tvm.script import tir as T @I.ir_module class Module: @T.prim_func def dense_loop( CSR_VAL: T.handle, INDICES: T.handle, IND_PTR: T.handle, VAL: T.handle, VEC: T.h

[Apache TVM Discuss] [Questions] Auto schedule performing worse than no schedule?

Prorgam with no schedule: ``` import time import tvm from tvm import relax from tvm.script import ir as I from tvm.script import relax as R from tvm.script import tir as T @I.ir_module class Module: @T.prim_func def dense_loop( VAL: T.handle, VEC: T.handle, OUT: