ViperEkura
7feeb0b93e
- Add TensorLayout enum (C++ + Python) to replace magic layout ints - Add C10_CUDA_CHECK post-launch error checking to all kernel entries - Add CUDAGuard + freqs_cis shape validation to rotary_emb.cu - Cache SM count to eliminate per-call cudaDeviceGetAttribute - Add DISPATCH_CAUSAL_MASK macro to deduplicate dispatcher if/else - Convert mask type hints from X|None to Optional[X]
44 lines
1.3 KiB
Plaintext
44 lines
1.3 KiB
Plaintext
#include "attn_dispatchers.cuh"
|
|
#include "attn_entry_utils.cuh"
|
|
|
|
torch::Tensor attn_paged_decode(
|
|
torch::Tensor q,
|
|
torch::Tensor page_table,
|
|
torch::Tensor k_cache,
|
|
torch::Tensor v_cache,
|
|
int64_t page_size,
|
|
int64_t kv_len,
|
|
c10::optional<torch::Tensor> mask,
|
|
int64_t causal_offset,
|
|
double scale,
|
|
int64_t layout
|
|
) {
|
|
PagedAttentionParams<bf16> p;
|
|
attn_pack_paged_params(q, page_table, k_cache, v_cache,
|
|
page_size, kv_len, mask, causal_offset, scale, layout, p);
|
|
|
|
auto O = torch::empty_strided(q.sizes(), q.strides(), q.options());
|
|
auto O_view = (layout == BLHD) ? O.transpose(1, 2) : O;
|
|
p.o = (bf16*)O_view.data_ptr();
|
|
|
|
alloc_split_partials(p);
|
|
DISPATCH_HEAD_DIM(p.head_dim, dispatch_paged_decode, p);
|
|
C10_CUDA_CHECK(cudaGetLastError());
|
|
return O;
|
|
}
|
|
|
|
PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
|
|
m.def("attn_paged_decode", &attn_paged_decode,
|
|
py::arg("q"),
|
|
py::arg("page_table"),
|
|
py::arg("k_cache"),
|
|
py::arg("v_cache"),
|
|
py::arg("page_size"),
|
|
py::arg("kv_len"),
|
|
py::arg("mask") = py::none(),
|
|
py::arg("causal_offset") = -1,
|
|
py::arg("scale") = 0.0,
|
|
py::arg("layout") = (int64_t)BHLD,
|
|
"Paged GQA decode — split-KV with direct page-table access.");
|
|
}
|