Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Compiling Issue] error: no instance of function template "flashinfer::BatchPrefillWithPagedKVCacheWrapper" matches the argument list #134

Closed
yintao-he opened this issue Feb 23, 2024 · 2 comments

Comments

@yintao-he
Copy link

Hi,

Thanks for the great framework! I am trying to compile and run the benchmark. However, I meet some problems when I compile decode kernel tests/benchmarks. After I run make -j12, I met this error if set(FLASHINFER_DECODE ON):

[ 98%] Building CUDA object CMakeFiles/bench_batch_decode.dir/src/bench_batch_decode.cu.o
/home/admin/llm-acceleration/flashinfer/src/bench_batch_decode.cu(156): error: no instance of function template "flashinfer::BatchPrefillWithPagedKVCacheWrapper" matches the argument list
argument types are: (flashinfer::BatchPrefillHandler *, half *, int32_t *, std::nullptr_t, flashinfer::paged_kv_t<flashinfer::PageStorage::kIndices, flashinfer::QKVLayout::kNHD, half, int32_t>, half *, std::nullptr_t, size_t, __nv_bool, const flashinfer::RotaryMode)
cudaError_t status = BatchPrefillWithPagedKVCacheWrapper<PageStorage::kIndices, kv_layout, T, T, int32_t>(
^
detected during instantiation of "void bench_flashinfer_batch_decode_with_prefill(nvbench::state &) [with T=half]"

1 error detected in the compilation of "/home/admin/llm-acceleration/flashinfer/src/bench_batch_decode.cu".
make[2]: *** [CMakeFiles/bench_batch_decode.dir/build.make:76: CMakeFiles/bench_batch_decode.dir/src/bench_batch_decode.cu.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:279: CMakeFiles/bench_batch_decode.dir/all] Error 2
make: *** [Makefile:136: all] Error 2

What can I do to figure it out? Thank you!

@yzh119
Copy link
Collaborator

yzh119 commented Feb 23, 2024

Hi @yintao-he , it's because of some code refactor in #69, and we have fixed them in #132.

@yzh119
Copy link
Collaborator

yzh119 commented Feb 25, 2024

#132 has been merged into mainline.

@yzh119 yzh119 closed this as completed Feb 25, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants