/* * SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved. * SPDX-License-Identifier: Apache-2.0 * * 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 "tensorrt_llm/common/logger.h" #include "tensorrt_llm/executor/executor.h" namespace tensorrt_llm::executor { CacheTransceiverConfig::CacheTransceiverConfig(std::optional backendType, std::optional maxNumTokens, std::optional kvTransferTimeoutMs, std::optional kvTransferSenderFutureTimeoutMs) : mBackendType(backendType) , mMaxTokensInBuffer(maxNumTokens) , mKvTransferTimeoutMs(kvTransferTimeoutMs) , mKvTransferSenderFutureTimeoutMs(kvTransferSenderFutureTimeoutMs) { } bool CacheTransceiverConfig::operator==(CacheTransceiverConfig const& other) const { return mMaxTokensInBuffer == other.mMaxTokensInBuffer && mBackendType == other.mBackendType && mKvTransferTimeoutMs == other.mKvTransferTimeoutMs; } void CacheTransceiverConfig::setBackendType(std::optional backendType) { mBackendType = backendType; } void CacheTransceiverConfig::setMaxTokensInBuffer(std::optional maxTokensInBuffer) { mMaxTokensInBuffer = maxTokensInBuffer; } void CacheTransceiverConfig::setKvTransferTimeoutMs(std::optional kvTransferTimeoutMs) { if (kvTransferTimeoutMs.has_value() && kvTransferTimeoutMs.value() <= 0) { TLLM_THROW("kvTransferTimeoutMs must be positive"); } mKvTransferTimeoutMs = kvTransferTimeoutMs; } void CacheTransceiverConfig::setKvTransferSenderFutureTimeoutMs(std::optional kvTransferSenderFutureTimeoutMs) { if (kvTransferSenderFutureTimeoutMs.has_value() && kvTransferSenderFutureTimeoutMs.value() <= 0) { TLLM_THROW("kvTransferSenderFutureTimeoutMs must be positive"); } mKvTransferSenderFutureTimeoutMs = kvTransferSenderFutureTimeoutMs; } std::optional CacheTransceiverConfig::getBackendType() const { return mBackendType; } std::optional CacheTransceiverConfig::getMaxTokensInBuffer() const { return mMaxTokensInBuffer; } std::optional CacheTransceiverConfig::getKvTransferTimeoutMs() const { return mKvTransferTimeoutMs; } std::optional CacheTransceiverConfig::getKvTransferSenderFutureTimeoutMs() const { return mKvTransferSenderFutureTimeoutMs; } } // namespace tensorrt_llm::executor