mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
ed887940d4
Replace libtensorrt_llm_nvrtc_wrapper.so with its source code, which consists of two parts: 1. NVRTC glue code 2. XQA kernel code During TensorRT-LLM build, XQA kernel code is embedded as C++ arries via gen_cpp_header.py and passed to NVRTC for JIT compilation. Signed-off-by: Ming Wei <2345434+ming-wei@users.noreply.github.com>
26 lines
853 B
C
26 lines
853 B
C
/*
|
|
* SPDX-FileCopyrightText: Copyright (c) 2023-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
* SPDX-License-Identifier: NVIDIA TensorRT Source Code License Agreement
|
|
*
|
|
* NVIDIA CORPORATION, its affiliates and licensors retain all intellectual
|
|
* property and proprietary rights in and to this material, related
|
|
* documentation and any modifications thereto. Any use, reproduction,
|
|
* disclosure or distribution of this material and related documentation
|
|
* without an express license agreement from NVIDIA CORPORATION or
|
|
* its affiliates is strictly prohibited.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include "defines.h"
|
|
#if SPEC_DEC
|
|
|
|
struct SpecDecParams
|
|
{
|
|
uint32_t qSeqLen;
|
|
uint32_t const* qCuSeqLens; // [nbReq + 1]
|
|
MaskType const* mask; // [nbReq][qSeqLen][divUp(qSeqLen, 32)] or [qCuSeqLen[nbReq]][divUp(qSeqLen, 32)]
|
|
};
|
|
|
|
#endif
|