GitHub – Deepseek-ai/DeepSeek-V3

We provide DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B overall criteria with 37B activated for each token. To accomplish efficient reasoning and cost-efficient training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were completely validated in DeepSeek-V2. Furthermore, DeepSeek-V3 leaders an auxiliary-loss-free strategy for load balancing and sets a multi-token forecast training goal for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning phases to completely harness its capabilities. Comprehensive examinations expose that DeepSeek-V3 outperforms other open-source designs and accomplishes efficiency equivalent to leading closed-source models. Despite its excellent performance, DeepSeek-V3 needs just 2.788 M H800 GPU hours for its complete training. In addition, its training process is incredibly steady. Throughout the whole training procedure, 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 effective architecture of DeepSeek-V2, we leader an auxiliary-loss-free technique for load balancing, which decreases the performance destruction that develops from encouraging load balancing.
– We examine a Multi-Token Prediction (MTP) goal and show it beneficial to model efficiency. It can also be used for speculative decoding for inference velocity.

Pre-Training: Towards Ultimate Training Efficiency

– We create an FP8 blended accuracy training structure and, for the very first time, validate the expediency and effectiveness of FP8 training on an incredibly massive design.
– Through co-design of algorithms, frameworks, and hardware, we conquer the communication traffic jam in cross-node MoE training, almost achieving full computation-communication overlap.
This substantially improves our training efficiency and decreases the training costs, allowing us to further scale up the design size without additional overhead.
– At an economical 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 greatest open-source base model. The subsequent training phases after pre-training require only 0.1 M GPU hours.

Post-Training: Knowledge Distillation from DeepSeek-R1

– We present an ingenious methodology to boil down reasoning capabilities from the long-Chain-of-Thought (CoT) design, specifically from among the DeepSeek R1 series designs, into basic LLMs, particularly DeepSeek-V3. Our pipeline elegantly includes the verification and reflection patterns of R1 into DeepSeek-V3 and notably improves its thinking efficiency. Meanwhile, we also keep 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 ensure optimum efficiency and flexibility, we have actually partnered with open-source neighborhoods and hardware suppliers to offer several ways to run the model in your area. For detailed guidance, take a look at Section 6: How_to Run_Locally.

For designers looking to dive deeper, we advise checking out README_WEIGHTS. md for information on the Main Model weights and the Multi-Token Prediction (MTP) Modules. Please note that MTP support 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 space not going beyond 0.3 are considered to be at the exact same level. DeepSeek-V3 attains the best efficiency on most standards, specifically on mathematics and code tasks. For more evaluation 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 designs are examined in a configuration that restricts the output length to 8K. Benchmarks consisting of less than 1000 samples are tested numerous times utilizing differing temperature settings to derive robust results. DeepSeek-V3 stands as the best-performing open-source model, and likewise shows competitive efficiency against frontier closed-source models.

Open Ended Generation Evaluation

English open-ended discussion evaluations. 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 deployed in your area using the following hardware and open-source neighborhood software application:

DeepSeek-Infer Demo: We provide a basic and light-weight demo for FP8 and BF16 inference.
SGLang: Fully support the DeepSeek-V3 model 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 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 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 embraced in our structure, we just provide FP8 weights. If you need BF16 weights for experimentation, you can use the offered conversion script to perform the transformation.

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 reasoning folder and install dependences listed in requirements.txt. Easiest way is to use a plan supervisor like conda or uv to create a 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 particular format:

Run

Then you can chat with DeepSeek-V3:

Or batch inference on a given file:

6.2 Inference with SGLang (advised)

SGLang currently supports MLA optimizations, DP Attention, FP8 (W8A8), FP8 KV Cache, and Torch Compile, delivering cutting edge latency and throughput performance among open-source structures.

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

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

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

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 (suggested)

LMDeploy, a versatile and high-performance inference and serving framework tailored for large language designs, now supports DeepSeek-V3. It offers both offline pipeline processing and online implementation abilities, effortlessly incorporating with .

For comprehensive detailed directions 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 model, using accuracy choices such as BF16 and INT4/INT8 weight-only. Support for FP8 is presently in development and will be released soon. You can access the customized branch of TRTLLM specifically for DeepSeek-V3 assistance through the following link to experience the brand-new functions directly: https://github.com/NVIDIA/TensorRT-LLM/tree/deepseek/examples/deepseek_v3.

6.5 Inference with vLLM (suggested)

vLLM v0.6.6 supports DeepSeek-V3 reasoning for FP8 and BF16 modes on both NVIDIA and AMD GPUs. Aside from basic methods, vLLM provides pipeline parallelism allowing you to run this design on multiple makers linked by networks. For in-depth guidance, please describe the vLLM guidelines. Please feel free to follow the improvement strategy also.

6.6 Recommended Inference Functionality with AMD GPUs

In cooperation with the AMD group, we have achieved Day-One assistance for AMD GPUs using SGLang, with full compatibility for both FP8 and BF16 precision. For comprehensive assistance, please refer to the SGLang guidelines.

6.7 Recommended Inference Functionality with Huawei Ascend NPUs

The MindIE framework from the Huawei Ascend neighborhood has successfully adjusted the BF16 version of DeepSeek-V3. For detailed assistance on Ascend NPUs, please follow the directions here.

7. License

This code repository is certified under the MIT License. Using DeepSeek-V3 Base/Chat models is subject to the Model License. DeepSeek-V3 series (consisting of Base and Chat) supports industrial use.