We provide DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total criteria with 37B activated for each token. To attain efficient inference and cost-efficient training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly verified in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free technique for load balancing and sets a multi-token prediction training goal for more powerful performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to completely harness its abilities. Comprehensive assessments expose that DeepSeek-V3 exceeds other open-source designs and achieves efficiency comparable to leading closed-source designs. Despite its excellent efficiency, DeepSeek-V3 requires just 2.788 M H800 GPU hours for its complete training. In addition, its training procedure is incredibly stable. Throughout the whole training process, we did not experience any irrecoverable loss spikes or perform any rollbacks.


2. Model Summary


Architecture: Innovative Load Balancing Strategy and Training Objective


- On top of the effective architecture of DeepSeek-V2, we leader an auxiliary-loss-free method for load balancing, which reduces the efficiency destruction that occurs from motivating load balancing.
- We examine a Multi-Token Prediction (MTP) objective and prove it advantageous to design performance. It can also be utilized for speculative decoding for reasoning velocity.


Pre-Training: Towards Ultimate Training Efficiency


- We develop an FP8 blended precision training structure and, for the very first time, verify the expediency and effectiveness of FP8 training on an incredibly large-scale model.
- Through co-design of algorithms, structures, and hardware, we get rid of the communication bottleneck in cross-node MoE training, nearly attaining full computation-communication overlap.
This significantly boosts our training efficiency and lowers the training costs, enabling us to even more scale up the design size without additional overhead.
- At a cost-effective expense of just 2.664 M H800 GPU hours, we finish the pre-training of DeepSeek-V3 on 14.8 T tokens, producing the presently strongest open-source base design. The subsequent training stages after pre-training need just 0.1 M GPU hours.


Post-Training: Knowledge Distillation from DeepSeek-R1


- We introduce an ingenious methodology to distill thinking capabilities from the long-Chain-of-Thought (CoT) design, particularly from one of the DeepSeek R1 series designs, into basic LLMs, especially DeepSeek-V3. Our pipeline elegantly integrates the confirmation and reflection patterns of R1 into DeepSeek-V3 and especially enhances its thinking performance. Meanwhile, we also preserve a control over the output design and length of DeepSeek-V3.


3. Model Downloads


The total size of DeepSeek-V3 designs on Hugging Face is 685B, that includes 671B of the Main Model weights and 14B of the Multi-Token Prediction (MTP) Module weights. **


To guarantee optimal efficiency and flexibility, we have actually partnered with open-source communities and hardware suppliers to supply multiple ways to run the model locally. For step-by-step assistance, have a look at Section 6: How_to Run_Locally.


For developers seeking to dive much deeper, we advise exploring README_WEIGHTS. md for details on the Main Model weights and the Multi-Token Prediction (MTP) Modules. Please note that MTP assistance is presently under active advancement within the community, and we invite your contributions and feedback.


4. Evaluation Results


Base Model


Standard Benchmarks


Best outcomes are displayed in vibrant. Scores with a gap not exceeding 0.3 are considered to be at the same level. DeepSeek-V3 achieves the best efficiency on many standards, specifically on math and code tasks. For more examination details, please inspect our paper.


Context Window


Evaluation results on the Needle In A Haystack (NIAH) tests. DeepSeek-V3 carries out well throughout all context window lengths as much as 128K.


Chat Model


Standard Benchmarks (Models bigger than 67B)


All models are examined in a setup that limits the output length to 8K. Benchmarks including fewer than 1000 samples are evaluated several times utilizing differing temperature settings to obtain robust last outcomes. DeepSeek-V3 stands as the best-performing open-source model, and likewise shows competitive performance versus frontier closed-source models.


Open Ended Generation Evaluation


English open-ended conversation assessments. For AlpacaEval 2.0, we utilize the length-controlled win rate as the metric.


5. Chat Website & API Platform


You can talk with DeepSeek-V3 on DeepSeek's official website: chat.deepseek.com


We likewise offer OpenAI-Compatible API at DeepSeek Platform: platform.deepseek.com


6. How to Run Locally


DeepSeek-V3 can be deployed locally utilizing the following hardware and open-source community software:


DeepSeek-Infer Demo: We supply a basic and lightweight demo for FP8 and BF16 inference.
SGLang: Fully support the DeepSeek-V3 design in both BF16 and FP8 reasoning modes, with Multi-Token Prediction coming soon.
LMDeploy: Enables efficient FP8 and BF16 reasoning for local and cloud implementation.
TensorRT-LLM: Currently supports BF16 inference and INT4/8 quantization, with FP8 assistance coming soon.
vLLM: Support DeepSeek-V3 design with FP8 and BF16 modes for tensor parallelism and pipeline parallelism.
AMD GPU: Enables running the DeepSeek-V3 model on AMD GPUs by means of SGLang in both BF16 and FP8 modes.
Huawei Ascend NPU: Supports running DeepSeek-V3 on Huawei Ascend gadgets.
Since FP8 training is natively adopted in our framework, we only provide FP8 weights. If you require BF16 weights for experimentation, you can utilize the offered conversion script to perform the improvement.


Here is an example of converting FP8 weights to BF16:


Hugging Face's Transformers has not been straight supported yet. **


6.1 Inference with DeepSeek-Infer Demo (example just)


System Requirements


Note


Linux with Python 3.10 just. Mac and Windows are not supported.


Dependencies:


Model Weights & Demo Code Preparation


First, clone our DeepSeek-V3 GitHub repository:


Navigate to the inference folder and set up dependencies noted in requirements.txt. Easiest way is to utilize a package supervisor like conda or uv to create a brand-new virtual environment and set up the dependences.


Download the model weights from Hugging Face, and put them into/ path/to/DeepSeek-V 3 folder.


Model Weights Conversion


Convert Hugging Face design weights to a specific format:


Run


Then you can chat with DeepSeek-V3:


Or batch reasoning on an offered file:


6.2 Inference with SGLang (advised)


SGLang currently supports MLA optimizations, DP Attention, FP8 (W8A8), FP8 KV Cache, and Torch Compile, providing state-of-the-art latency and throughput efficiency amongst open-source frameworks.


Notably, SGLang v0.4.1 completely supports running DeepSeek-V3 on both NVIDIA and AMD GPUs, making it a highly flexible and robust option.


SGLang likewise supports multi-node tensor parallelism, enabling you to run this design on multiple network-connected makers.


Multi-Token Prediction (MTP) is in advancement, and development can be tracked in the optimization strategy.


Here are the launch guidelines from the SGLang group: https://github.com/sgl-project/sglang/t … eepseek_v3


6.3 Inference with LMDeploy (recommended)


LMDeploy, a flexible and high-performance inference and serving framework customized for big language designs, now supports DeepSeek-V3. It uses both offline pipeline processing and online implementation capabilities, seamlessly incorporating with PyTorch-based workflows.


For extensive step-by-step guidelines on running DeepSeek-V3 with LMDeploy, please refer to here: InternLM/lmdeploy # 2960


6.4 Inference with TRT-LLM (suggested)


TensorRT-LLM now supports the DeepSeek-V3 design, offering accuracy choices such as BF16 and INT4/INT8 weight-only. Support for FP8 is currently in development and will be launched quickly. You can access the custom branch of TRTLLM specifically for DeepSeek-V3 assistance through the following link to experience the brand-new functions straight: https://github.com/NVIDIA/TensorRT-LLM/ … epseek_v3.


6.5 Inference with vLLM (advised)


vLLM v0.6.6 supports DeepSeek-V3 reasoning for FP8 and BF16 modes on both NVIDIA and AMD GPUs. Aside from standard techniques, vLLM provides pipeline parallelism permitting you to run this design on multiple devices connected by networks. For detailed assistance, please refer to the vLLM guidelines. Please feel totally free to follow the enhancement strategy as well.


6.6 Recommended Inference Functionality with AMD GPUs


In cooperation with the AMD group, we have actually accomplished Day-One support for AMD GPUs using SGLang, with full compatibility for both FP8 and BF16 accuracy. For in-depth guidance, please refer to the SGLang directions.


6.7 Recommended Inference Functionality with Huawei Ascend NPUs


The MindIE framework from the Huawei Ascend neighborhood has actually effectively adapted the BF16 variation of DeepSeek-V3. For step-by-step assistance on Ascend NPUs, please follow the guidelines here.


7. License


This code repository is certified under the MIT License. Making use of DeepSeek-V3 Base/Chat models goes through the Model License. DeepSeek-V3 series (including Base and Chat) supports business usage.