mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
dbaddb3a29
* Adding two-shot allreduce kernel and mnnvl multicasting buffergit gffe Signed-off-by: Shiyu Li <shili@nvidia.com> Adding comments Signed-off-by: Shiyu Li <shili@nvidia.com> Add unittest of the twoshot kernel. Signed-off-by: Shiyu Li <shili@nvidia.com> Update dispatch logic Signed-off-by: Shiyu Li <shili@nvidia.com> Use cpu barrier instead of GPU at init Signed-off-by: Shiyu Li <shili@nvidia.com> Merge dispatch logic fix Signed-off-by: Shiyu Li <shili@nvidia.com> Update the kernel to use GPU-managed buffer Signed-off-by: Shiyu Li <shili@nvidia.com> * Refine Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Clean code Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Fix compile error Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Fix issue Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Clean up Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Simplify AllReduce interface Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Rename Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Fix warning Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Tidy code Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Rename Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Fix compile error Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Refine Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Skip ut for no_fusion Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> * Refine Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> --------- Signed-off-by: Shiyu Li <shili@nvidia.com> Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com> Co-authored-by: Shiyu Li <shili@nvidia.com>
62 lines
1.5 KiB
C++
62 lines
1.5 KiB
C++
/*
|
|
* Copyright (c) 2022-2024, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* 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.
|
|
*/
|
|
#pragma once
|
|
|
|
#include <NvInferRuntime.h>
|
|
#include <array>
|
|
#include <cstddef>
|
|
#include <cstdint>
|
|
|
|
namespace tensorrt_llm::kernels::mnnvl
|
|
{
|
|
struct AllReduceParams
|
|
{
|
|
int nranks;
|
|
int rank;
|
|
nvinfer1::DataType dtype;
|
|
int buffer_M;
|
|
int num_tokens;
|
|
int token_dim;
|
|
void** buffer_ptrs_dev;
|
|
void* multicast_ptr;
|
|
void* buffer_flags;
|
|
bool wait_for_results;
|
|
|
|
void* input;
|
|
void* output;
|
|
cudaStream_t stream;
|
|
};
|
|
|
|
void twoshot_allreduce_op(AllReduceParams const& params);
|
|
|
|
struct RMSNormParams
|
|
{
|
|
void* residual_output;
|
|
void* output;
|
|
void const* input;
|
|
void const* gamma;
|
|
double epsilon;
|
|
void* residual;
|
|
uint32_t* buffer_flags;
|
|
int batch;
|
|
int hidden_dim;
|
|
cudaStream_t stream;
|
|
nvinfer1::DataType dtype;
|
|
};
|
|
|
|
void twoshot_rmsnorm_op(RMSNormParams const& params);
|
|
} // namespace tensorrt_llm::kernels::mnnvl
|