State-of-the-art, high-efficiency LLM excelling in reasoning, math, and coding.

DeepSeek-R1 is a first-generation reasoning model trained using large-scale reinforcement learning (RL) to solve complex reasoning tasks across domains such as math, code, and language. The model leverages RL to develop reasoning capabilities, which are further enhanced through supervised fine-tuning (SFT) to improve readability and coherence.

Jan 30, 2025 · The DeepSeek-R1 NIM microservice can deliver up to 3,872 tokens per second on a single NVIDIA HGX H200 system. Developers can test and experiment with the application programming interface (API), which is expected to be available soon as a downloadable NIM microservice, part of the NVIDIA AI Enterprise software platform.

下一代 NVIDIA Blackwell 架构将凭借第五代张量核心 (Tensor Cores) 以及专为推理优化的 72-GPU NVLink 域，为 DeepSeek-R1 这类推理模型的测试时缩放能力带来飞跃式提升。

Model Overview Description: DeepSeek-R1 is a first-generation reasoning model trained using large-scale reinforcement learning (RL) to solve complex reasoning tasks across domains such as math, code, and language. ... NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development ...

Jan 31, 2025 · 就在刚刚英伟达宣布 NVIDIA NIM 上线DeepSeek-R1。 而且注册就有免费推理次数（普通邮箱1000次免费推理，企业邮箱5000次免费推理）。 NVIDIA NIM（Inference Microservices）是NVIDIA AI Enterprise 的一部分，旨在加速生成式人工智能（AI）模型的部署。 它是一套经过优化的 云原生 微服务，简化了AI 模型在云、数据中心和GPU 加速工作站中的部署流程 。 NIM 提供预构建的容器工具，支持多种AI 模型，包括 大型语言模型（LLM） 、语音AI …

Jan 22, 2025 · 本文将详细介绍如何在NVIDIA 3090显卡上部署DeepSeek-R1 32B模型，并提供优化的vLLM配置参数，使其在显存占用和性能上达到最佳平衡。 检查显卡驱动：能执行 nvidia-smi。 安装 PyTorch：安装与CUDA版本匹配的PyTorch，确保能够支持 混合精度 计算。 安装vLLM：使用pip安装最新版本的vllm。 使用NVIDIA 3090部署DeepSeek-R1 32B模型：vLLM配置指南深度学习模型的部署一直是AI开发中至关重要的一环，尤其是在显存资源有限的情况下， …

2025年1月31日，英伟达宣布，DeepSeek-R1模型现已作为NVIDIA NIM微服务预览版提供。DeepSeek-R1 NIM 微服务可以在单个 NVIDIA HGX H200 系统上每秒提供多达 3,872 tokens。 [14] 同日，DeepSeek R1 671b已作为英伟达NIM微服务预览版发布。 [15]

Jan 31, 2025 · Experience the power of DeepSeek-R1 and RTX AI PCs through a vast ecosystem of software, including Llama.cpp, Ollama, LM Studio, AnythingLLM, Jan.AI, GPT4All and OpenWebUI, for inference. Plus, use Unsloth to fine-tune the models with custom data.

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks ...