`Statistics.mean(Float32, arr, dims=1)` throws `KernelError`

```julia-repl
julia> using CUDA, Statistics

julia> a_gpu = CUDA.rand(Int32, 100, 100)
julia> m_gpu = mean(Float32, a_gpu, dims=1)
```

resulted in the following error.

```
GPU compilation of MethodInstance for CUDA.partial_mapreduce_grid(::ComposedFunction{Base.Fix1{typeof(*), Float64}, Type{Float32}}, ::typeof(Base.add_sum), ::Float64, ::CartesianIndices{2, Tuple{Base.OneTo{Int64}, Base.OneTo{Int64}}}, ::CartesianIndices{2, Tuple{Base.OneTo{Int64}, Base.OneTo{Int64}}}, ::Val{true}, ::CuDeviceMatrix{Float64, 1}, ::CuDeviceMatrix{Int32, 1}) failed
KernelError: passing non-bitstype argument

Argument 2 to your kernel function is of type ComposedFunction{Base.Fix1{typeof(*), Float64}, Type{Float32}}, which is not a bitstype:
.inner is of type Type{Float32} which is not isbits.

Only bitstypes, which are "plain data" types that are immutable
and contain no references to other values, can be used in GPU kernels.
For more information, see the `Base.isbitstype` function.

Stacktrace:
[1] check_invocation(job::GPUCompiler.CompilerJob)
@ GPUCompiler /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/validation.jl:108
[2] macro expansion
@ /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/driver.jl:87 [inlined]
[3] macro expansion
@ /pscratch/sd/y/yuanru/.julia/packages/Tracy/slmNc/src/tracepoint.jl:163 [inlined]
[4] compile_unhooked(output::Symbol, job::GPUCompiler.CompilerJob; kwargs::@Kwargs{})
@ GPUCompiler /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/driver.jl:85
[5] compile_unhooked
@ /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/driver.jl:80 [inlined]
[6] compile(target::Symbol, job::GPUCompiler.CompilerJob; kwargs::@Kwargs{})
@ GPUCompiler /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/driver.jl:67
[7] compile
@ /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/driver.jl:55 [inlined]
[8] #1182
@ /pscratch/sd/y/yuanru/.julia/packages/CUDA/ja0IX/src/compiler/compilation.jl:250 [inlined]
[9] JuliaContext(f::CUDA.var"#1182#1185"{GPUCompiler.CompilerJob{GPUCompiler.PTXCompilerTarget, CUDA.CUDACompilerParams}}; kwargs::@Kwargs{})
@ GPUCompiler /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/driver.jl:34
[10] JuliaContext(f::Function)
@ GPUCompiler /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/driver.jl:25
[11] compile(job::GPUCompiler.CompilerJob)
@ CUDA /pscratch/sd/y/yuanru/.julia/packages/CUDA/ja0IX/src/compiler/compilation.jl:249
[12] actual_compilation(cache::Dict{Any, CuFunction}, src::Core.MethodInstance, world::UInt64, cfg::GPUCompiler.CompilerConfig{GPUCompiler.PTXCompilerTarget, CUDA.CUDACompilerParams}, compiler::typeof(CUDA.compile), linker::typeof(CUDA.link))
@ GPUCompiler /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/execution.jl:245
[13] cached_compilation(cache::Dict{Any, CuFunction}, src::Core.MethodInstance, cfg::GPUCompiler.CompilerConfig{GPUCompiler.PTXCompilerTarget, CUDA.CUDACompilerParams}, compiler::Function, linker::Function)
@ GPUCompiler /pscratch/sd/y/yuanru/.julia/packages/GPUCompiler/Ecaql/src/execution.jl:159
[14] macro expansion
@ /pscratch/sd/y/yuanru/.julia/packages/CUDA/ja0IX/src/compiler/execution.jl:373 [inlined]
[15] macro expansion
@ ./lock.jl:267 [inlined]
[16] cufunction(f::typeof(CUDA.partial_mapreduce_grid), tt::Type{Tuple{ComposedFunction{Base.Fix1{typeof(*), Float64}, Type{Float32}}, typeof(Base.add_sum), Float64, CartesianIndices{2, Tuple{Base.OneTo{Int64}, Base.OneTo{Int64}}}, CartesianIndices{2, Tuple{Base.OneTo{Int64}, Base.OneTo{Int64}}}, Val{true}, CuDeviceMatrix{Float64, 1}, CuDeviceMatrix{Int32, 1}}}; kwargs::@Kwargs{})
@ CUDA /pscratch/sd/y/yuanru/.julia/packages/CUDA/ja0IX/src/compiler/execution.jl:368
[17] cufunction(f::typeof(CUDA.partial_mapreduce_grid), tt::Type{Tuple{ComposedFunction{Base.Fix1{typeof(*), Float64}, Type{Float32}}, typeof(Base.add_sum), Float64, CartesianIndices{2, Tuple{Base.OneTo{Int64}, Base.OneTo{Int64}}}, CartesianIndices{2, Tuple{Base.OneTo{Int64}, Base.OneTo{Int64}}}, Val{true}, CuDeviceMatrix{Float64, 1}, CuDeviceMatrix{Int32, 1}}})
@ CUDA /pscratch/sd/y/yuanru/.julia/packages/CUDA/ja0IX/src/compiler/execution.jl:365
[18] macro expansion
@ /pscratch/sd/y/yuanru/.julia/packages/CUDA/ja0IX/src/compiler/execution.jl:112 [inlined]
[19] mapreducedim!(f::ComposedFunction{Base.Fix1{typeof(*), Float64}, Type{Float32}}, op::typeof(Base.add_sum), R::CuArray{Float64, 2, CUDA.DeviceMemory}, A::CuArray{Int32, 2, CUDA.DeviceMemory}; init::Float64)
@ CUDA /pscratch/sd/y/yuanru/.julia/packages/CUDA/ja0IX/src/mapreduce.jl:229
[20] mapreducedim!
@ /pscratch/sd/y/yuanru/.julia/packages/CUDA/ja0IX/src/mapreduce.jl:169 [inlined]
[21] _mapreduce(f::ComposedFunction{Base.Fix1{typeof(*), Float64}, Type{Float32}}, op::typeof(Base.add_sum), As::CuArray{Int32, 2, CUDA.DeviceMemory}; dims::Int64, init::Nothing)
@ GPUArrays /pscratch/sd/y/yuanru/.julia/packages/GPUArrays/u6tui/src/host/mapreduce.jl:76
[22] mapreduce(::Function, ::Function, ::CuArray{Int32, 2, CUDA.DeviceMemory}; dims::Int64, init::Nothing)
@ GPUArrays /pscratch/sd/y/yuanru/.julia/packages/GPUArrays/u6tui/src/host/mapreduce.jl:28
[23] mapreduce
@ /pscratch/sd/y/yuanru/.julia/packages/GPUArrays/u6tui/src/host/mapreduce.jl:28 [inlined]
[24] _sum
@ ./reducedim.jl:1041 [inlined]
[25] sum
@ ./reducedim.jl:1013 [inlined]
[26] _mean
@ /pscratch/sd/y/yuanru/.julia/packages/GPUArrays/u6tui/src/host/statistics.jl:37 [inlined]
[27] #mean#1
@ /global/cfs/cdirs/m2676/users/yuanru/.juliaup/juliaup/julia-1.10.10+0.x64.linux.gnu/share/julia/stdlib/v1.10/Statistics/src/Statistics.jl:104 [inlined]
[28] top-level scope
@ REPL[5]:1
[29] top-level scope
@ none:1
```

Note that it works if I remove either `Float32` or `dims=1`

```julia-repl
julia> m = mean(Float32, a)
2.6236948f6
julia> m = mean(a, dims=1)
1×100 CuArray{Float64, 2, CUDA.DeviceMemory}:
6.44418e7 1.63643e8 5.03201e7 4.19325e7 -9.81884e7 -1.30971e8 -1.48728e8 … 1.86605e7 -5.30929e6 9.33825e7 -6.25027e7 8.92984e7 5.62057e7 6.36258e7
```

The CUDA version is v5.8.2.

Version Info

```
Julia Version 1.10.10
Commit 95f30e51f41 (2025-06-27 09:51 UTC)
Build Info:
Official https://julialang.org/ release
Platform Info:
OS: Linux (x86_64-linux-gnu)
CPU: 256 × AMD EPYC 7713 64-Core Processor
WORD_SIZE: 64
LIBM: libopenlibm
LLVM: libLLVM-15.0.7 (ORCJIT, znver3)
Threads: 1 default, 0 interactive, 1 GC (on 256 virtual cores)
Environment:
JULIA_PROJECT = @work
JULIA_DEPOT_PATH = /pscratch/sd/y/yuanru/.julia
```

Reproduce the example with Julia 1.10.10 and CUDA v5.8.2, then read GPUArrays/src/host/mapreduce.jl and GPUArrays/src/host/statistics.jl, especially the mapreducedim! path shown in the trace. Compare the working calls with mean(Float32, a_gpu, dims=1); done means that call completes without KernelError and returns the expected reduced result.

Written by the indexing model from the issue text.