GitHub – Deepseek-ai/DeepSeek-V3

We provide DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total specifications with 37B triggered for each token. To accomplish effective inference and economical training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were completely verified in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free method for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion varied and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to completely harness its abilities. Comprehensive assessments expose that DeepSeek-V3 surpasses other open-source designs and accomplishes performance comparable to leading closed-source models. Despite its exceptional performance, DeepSeek-V3 requires just 2.788 M H800 GPU hours for its complete training. In addition, its training process is incredibly stable. Throughout the whole training process, we did not experience any irrecoverable loss spikes or carry out any rollbacks.

2. Model Summary

Architecture: Innovative Load Balancing Strategy and Training Objective

– On top of the efficient architecture of DeepSeek-V2, we pioneer an auxiliary-loss-free strategy for load balancing, which minimizes the performance degradation that occurs from encouraging load balancing.
– We investigate a Multi-Token Prediction (MTP) objective and prove it beneficial to model performance. It can also be utilized for speculative decoding for inference velocity.

Pre-Training: Towards Efficiency

– We design an FP8 blended accuracy training framework and, for the very first time, validate the feasibility and efficiency of FP8 training on an extremely large-scale design.
– Through co-design of algorithms, structures, and hardware, we get rid of the communication bottleneck in cross-node MoE training, almost accomplishing full computation-communication overlap.
This considerably enhances our training efficiency and minimizes the training expenses, allowing us to even more scale up the design size without additional overhead.
– At a cost-effective cost of only 2.664 M H800 GPU hours, we finish the pre-training of DeepSeek-V3 on 14.8 T tokens, producing the currently greatest open-source base model. The subsequent training stages after pre-training need only 0.1 M GPU hours.

Post-Training: Knowledge Distillation from DeepSeek-R1

– We introduce an innovative approach to distill thinking abilities from the long-Chain-of-Thought (CoT) model, particularly from among the DeepSeek R1 series models, into standard LLMs, particularly DeepSeek-V3. Our pipeline elegantly integrates the confirmation and reflection patterns of R1 into DeepSeek-V3 and significantly improves its thinking efficiency. Meanwhile, we likewise keep a control over the output style 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 versatility, we have actually partnered with open-source communities and hardware vendors to offer numerous methods to run the model locally. For step-by-step assistance, have a look at Section 6: How_to Run_Locally.

For developers aiming to dive deeper, we recommend exploring README_WEIGHTS. md for information on the Main Model weights and the Multi-Token Prediction (MTP) Modules. Please note that MTP support is currently under active development within the community, and we invite your contributions and feedback.

4. Evaluation Results

Base Model

Standard Benchmarks

Best results are shown in strong. Scores with a gap not surpassing 0.3 are thought about to be at the same level. DeepSeek-V3 achieves the finest efficiency on many benchmarks, particularly on mathematics and code tasks. For more assessment details, please inspect our paper.

Context Window

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

Chat Model

Standard Benchmarks (Models larger than 67B)

All models are evaluated in a configuration that limits the output length to 8K. Benchmarks containing fewer than 1000 samples are evaluated multiple times using differing temperature level settings to obtain robust last outcomes. DeepSeek-V3 stands as the best-performing open-source model, and likewise displays competitive performance against frontier closed-source models.

Open Ended Generation Evaluation

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

5. Chat Website & API Platform

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

We also provide OpenAI-Compatible API at DeepSeek Platform: platform.deepseek.com

6. How to Run Locally

DeepSeek-V3 can be released in your area using the following hardware and open-source community software application:

DeepSeek-Infer Demo: We provide a simple and light-weight demo for FP8 and BF16 reasoning.
SGLang: Fully support the DeepSeek-V3 design in both BF16 and FP8 inference modes, with Multi-Token Prediction coming soon.
LMDeploy: Enables efficient FP8 and BF16 inference for regional and cloud implementation.
TensorRT-LLM: Currently supports BF16 inference and INT4/8 quantization, with FP8 assistance coming quickly.
vLLM: Support DeepSeek-V3 model with FP8 and BF16 modes for tensor parallelism and pipeline parallelism.
AMD GPU: Enables running the DeepSeek-V3 design on AMD GPUs through 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 structure, we just offer FP8 weights. If you need BF16 weights for experimentation, you can utilize the supplied conversion script to perform the transformation.

Here is an example of converting FP8 weights to BF16:

Hugging Face’s Transformers has not been directly 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 install dependencies listed in requirements.txt. Easiest way is to use a bundle manager like conda or uv to create a brand-new virtual environment and install the dependencies.

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

Model Weights Conversion

Convert Hugging Face model weights to a specific format:

Run

Then you can chat with DeepSeek-V3:

Or batch reasoning on a provided file:

6.2 Inference with SGLang (suggested)

SGLang currently supports MLA optimizations, DP Attention, FP8 (W8A8), FP8 KV Cache, and Torch Compile, delivering modern latency and throughput efficiency amongst open-source frameworks.

Notably, SGLang v0.4.1 fully 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 model on multiple network-connected machines.

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

Here are the launch directions from the SGLang team: https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3

6.3 Inference with LMDeploy (recommended)

LMDeploy, a flexible and high-performance reasoning and serving framework tailored for big language designs, now supports DeepSeek-V3. It offers both offline pipeline processing and online release abilities, flawlessly incorporating with PyTorch-based workflows.

For detailed detailed directions on running DeepSeek-V3 with LMDeploy, please describe here: InternLM/lmdeploy # 2960

6.4 Inference with TRT-LLM (advised)

TensorRT-LLM now supports the DeepSeek-V3 model, offering accuracy options such as BF16 and INT4/INT8 weight-only. Support for FP8 is presently in development and will be launched quickly. You can access the custom-made branch of TRTLLM specifically for DeepSeek-V3 support through the following link to experience the new functions directly: https://github.com/NVIDIA/TensorRT-LLM/tree/deepseek/examples/deepseek_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 methods, vLLM provides pipeline parallelism allowing you to run this model on numerous makers linked by networks. For in-depth assistance, please refer to the vLLM directions. Please feel complimentary to follow the enhancement plan as well.

6.6 Recommended Inference Functionality with AMD GPUs

In partnership with the AMD group, we have achieved Day-One assistance for AMD GPUs utilizing SGLang, with complete compatibility for both FP8 and BF16 precision. For comprehensive guidance, please refer to the SGLang directions.

6.7 Recommended Inference Functionality with Huawei Ascend NPUs

The MindIE structure from the Huawei Ascend community has effectively adapted the BF16 version of DeepSeek-V3. For detailed guidance on Ascend NPUs, please follow the directions here.

7. License

This code repository is certified under the MIT License. The usage of DeepSeek-V3 Base/Chat designs goes through the Model License. DeepSeek-V3 series (consisting of Base and Chat) supports industrial use.