[Bug] `relax.build` crashes with an `AttributeError` during the dlight GPU scheduling pass

[XYZboom]

Expected behavior

relax.build(mod, target="cuda") should compile successfully for any valid Relax IR module containing relax.op.nn.conv2d. The compiled module should execute and produce correct convolution results.

Actual behavior

relax.build crashes with an AttributeError during the dlight GPU scheduling pass:

AttributeError: 'FloorDiv' object has no attribute 'value'

Environment

• OS: Linux (x86_64, conda environment)
• GPU: NVIDIA GeForce RTX 3080 Ti (12GB VRAM)
• CUDA driver: 580.76.05
• TVM version: 0.25.0.post1 (installed via pip)
• Target: cuda (GPU compilation)
• Python: 3.12

Steps to reproduce

from tvm import relax

bb = relax.BlockBuilder()
v = relax.Var("v", relax.TensorStructInfo(
    shape=relax.ShapeExpr([1, 1, 3, 10]), dtype="float32"))
w = relax.Var("w", relax.TensorStructInfo(
    shape=relax.ShapeExpr([1, 1, 1, 2]), dtype="float32"))
with bb.function("f", [v, w]):
    c = bb.emit(relax.op.nn.conv2d(v, w,
        strides=[1, 1], padding=[0, 0], dilation=[1, 1], groups=1))
    bb.emit_func_output(c)
mod = bb.get()
ex = relax.build(mod, target="cuda")

Triage

• bug
• CUDA
• dlight
• gemv
• conv2d
• needs-triage
• needs-triage

[XYZboom]

error:

Target cuda missing 'max_shared_memory_per_block'; using 49152 bytes.
Traceback (most recent call last):
  File "/root/autodl-tmp/data/AIFuzzerData/tvm/20047/main.py", line 26, in <module>
    ex = relax.build(mod, target="cuda")
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/miniconda3/lib/python3.12/site-packages/tvm/relax/vm_build.py", line 270, in build
    mod = relax_pipeline(mod)
          ^^^^^^^^^^^^^^^^^^^
  File "/root/miniconda3/lib/python3.12/site-packages/tvm/ir/transform.py", line 171, in __call__
    return _ffi_transform_api.RunPass(self, mod)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "python/tvm_ffi/cython/function.pxi", line 968, in tvm_ffi.core.Function.__call__
  File "<unknown>", line 0, in TVMFFIPyCallback(void*, TVMFFIAny const*, int, TVMFFIAny*)
  File "<unknown>", line 0, in TVMFFIPyCallManager::ForwardPyErrorToFFI()
  File "<unknown>", line 0, in TVMFFICyErrorSetRaisedFromPyError(_object*)
  File "/root/miniconda3/lib/python3.12/site-packages/tvm/relax/backend/cuda/pipeline.py", line 87, in _pipeline
    mod = seq(mod)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/ir/transform.py", line 171, in __call__
    return _ffi_transform_api.RunPass(self, mod)

  File "python/tvm_ffi/cython/function.pxi", line 968, in tvm_ffi.core.Function.__call__
  File "<unknown>", line 0, in TVMFFIPyCallback(void*, TVMFFIAny const*, int, TVMFFIAny*)
  File "<unknown>", line 0, in TVMFFIPyCallManager::ForwardPyErrorToFFI()
  File "<unknown>", line 0, in TVMFFICyErrorSetRaisedFromPyError(_object*)
  File "/root/miniconda3/lib/python3.12/site-packages/tvm/ir/transform.py", line 238, in _pass_func
    return inst.transform_module(mod, ctx)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/base/transform.py", line 70, in transform_module
    sch = _apply_rules(func, target, self.rules, tunable=False)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/base/transform.py", line 88, in _apply_rules
    space = rule.apply(func, target, tunable)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/gpu/gemv.py", line 79, in apply
    return self.sch_inner_reduction(sch, target, block, vector_input_buffers, epilogue)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/gpu/gemv.py", line 412, in sch_inner_reduction
    return apply(

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/gpu/gemv.py", line 228, in apply
    assert sch.get(ts_o).extent.value == 1

AttributeError: 'FloorDiv' object has no attribute 'value'

[XYZboom]

A variant:

import tvm
from tvm import relax
import numpy as np

bb = relax.BlockBuilder()

# Minimal trigger: single conv2d, N=1, C_in=1, C_out=1, output spatial dims > 1
v_input = relax.Var("input", relax.TensorStructInfo(shape=relax.ShapeExpr([1, 1, 6, 8]), dtype="float32"))
v_weight = relax.Var("weight", relax.TensorStructInfo(shape=relax.ShapeExpr([1, 1, 1, 3]), dtype="float32"))

with bb.function("main", [v_input, v_weight]):
    v_out = bb.emit(relax.op.nn.conv2d(v_input, v_weight, strides=[1, 1], padding=[0, 0], dilation=[1, 1], groups=1))
    bb.emit_func_output(v_out)

mod = bb.get()

ex = relax.build(mod, target="cuda")
vm = relax.VirtualMachine(ex, tvm.cuda())

np_input = np.random.uniform(0.0, 1.0, size=(1, 1, 6, 8)).astype(np.float32)
np_weight = np.random.uniform(-0.1, 0.1, size=(1, 1, 1, 3)).astype(np.float32)

result = vm["main"](tvm.runtime.tensor(np_input, device=tvm.cuda()), tvm.runtime.tensor(np_weight, device=tvm.cuda()))
print("Execution: OK")

Error log that has the same stack but different exception:

Target cuda missing 'max_shared_memory_per_block'; using 49152 bytes.
Traceback (most recent call last):
  File "/root/autodl-tmp/data/maybeBug/tvm_gemv_assert_value/main.py", line 17, in <module>
    ex = relax.build(mod, target="cuda")
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/miniconda3/lib/python3.12/site-packages/tvm/relax/vm_build.py", line 270, in build
    mod = relax_pipeline(mod)
          ^^^^^^^^^^^^^^^^^^^
  File "/root/miniconda3/lib/python3.12/site-packages/tvm/ir/transform.py", line 171, in __call__
    return _ffi_transform_api.RunPass(self, mod)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "python/tvm_ffi/cython/function.pxi", line 968, in tvm_ffi.core.Function.__call__
  File "<unknown>", line 0, in TVMFFIPyCallback(void*, TVMFFIAny const*, int, TVMFFIAny*)
  File "<unknown>", line 0, in TVMFFIPyCallManager::ForwardPyErrorToFFI()
  File "<unknown>", line 0, in TVMFFICyErrorSetRaisedFromPyError(_object*)
  File "/root/miniconda3/lib/python3.12/site-packages/tvm/relax/backend/cuda/pipeline.py", line 87, in _pipeline
    mod = seq(mod)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/ir/transform.py", line 171, in __call__
    return _ffi_transform_api.RunPass(self, mod)

  File "python/tvm_ffi/cython/function.pxi", line 968, in tvm_ffi.core.Function.__call__
  File "<unknown>", line 0, in TVMFFIPyCallback(void*, TVMFFIAny const*, int, TVMFFIAny*)
  File "<unknown>", line 0, in TVMFFIPyCallManager::ForwardPyErrorToFFI()
  File "<unknown>", line 0, in TVMFFICyErrorSetRaisedFromPyError(_object*)
  File "/root/miniconda3/lib/python3.12/site-packages/tvm/ir/transform.py", line 238, in _pass_func
    return inst.transform_module(mod, ctx)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/base/transform.py", line 70, in transform_module
    sch = _apply_rules(func, target, self.rules, tunable=False)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/base/transform.py", line 88, in _apply_rules
    space = rule.apply(func, target, tunable)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/gpu/gemv.py", line 79, in apply
    return self.sch_inner_reduction(sch, target, block, vector_input_buffers, epilogue)

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/gpu/gemv.py", line 412, in sch_inner_reduction
    return apply(

  File "/root/miniconda3/lib/python3.12/site-packages/tvm/s_tir/dlight/gpu/gemv.py", line 228, in apply
    assert sch.get(ts_o).extent.value == 1

AssertionError