mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
bb7bcc75c2
* Fallback to NCCL for various patterns when input size is large. Move the previous implementation to cpp side. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com> * Revising. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com> --------- Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
29 lines
987 B
C++
29 lines
987 B
C++
/*
|
|
* Copyright (c) 2025, 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 "tensorrt_llm/common/cudaUtils.h"
|
|
#include "tensorrt_llm/thop/thUtils.h"
|
|
|
|
#include <ATen/cuda/EmptyTensor.h>
|
|
#include <cstdint>
|
|
|
|
namespace torch_ext
|
|
{
|
|
std::tuple<torch::Tensor, torch::Tensor> fp4_quantize(torch::Tensor const& self, torch::Tensor const& globalScale,
|
|
int64_t sfVecSize, bool sfUseUE8M0, bool isSfSwizzledLayout);
|
|
}
|