28 lines
1.1 KiB
Plaintext
28 lines
1.1 KiB
Plaintext
/*
|
|
* Copyright (c) 2023-2025 by FlashInfer team.
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
#include "pytorch_extension_utils.h"
|
|
#include "single_prefill_config.inc"
|
|
|
|
void single_prefill_with_kv_cache(at::Tensor q, at::Tensor k, at::Tensor v, at::Tensor tmp,
|
|
at::Tensor o, std::optional<at::Tensor> maybe_lse,
|
|
int64_t mask_mode_code, int64_t layout,
|
|
int64_t window_left ADDITIONAL_FUNC_PARAMS);
|
|
|
|
TORCH_LIBRARY_FRAGMENT(TORCH_EXTENSION_NAME, m) {
|
|
// Single-request prefill attention with KV-Cache operator
|
|
m.def("run", single_prefill_with_kv_cache);
|
|
}
|