GitHub – Deepseek-ai/DeepSeek-V3

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 validated in DeepSeek-V2. Furthermore, DeepSeek-V3 leaders an auxiliary-loss-free technique for load balancing and sets a multi-token prediction training objective for more powerful efficiency. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive examinations expose that DeepSeek-V3 surpasses other open-source designs and achieves performance equivalent to leading closed-source designs. Despite its exceptional efficiency, DeepSeek-V3 requires only 2.788 M H800 GPU hours for its full training. In addition, its training process is extremely steady. Throughout the whole training procedure, 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 pioneer an auxiliary-loss-free strategy for load balancing, which lessens the performance degradation that arises from motivating load balancing.
– We examine a Multi-Token Prediction (MTP) goal and prove it useful to design performance. It can also be used for speculative decoding for inference acceleration.

Pre-Training: Towards Ultimate Training Efficiency

– We develop an FP8 mixed precision training framework and, for the very first time, confirm the feasibility and effectiveness of FP8 training on a very large-scale model.
– Through co-design of algorithms, structures, and hardware, we conquer the interaction traffic jam in cross-node MoE training, almost achieving full computation-communication overlap.
This substantially boosts our training efficiency and minimizes the training costs, allowing us to further scale up the model size without extra overhead.
– At a cost-effective cost of just 2.664 M H800 GPU hours, we complete the pre-training of DeepSeek-V3 on 14.8 T tokens, the currently greatest open-source base model. The subsequent training stages after pre-training require just 0.1 M GPU hours.

Post-Training: Knowledge Distillation from DeepSeek-R1

– We present an ingenious approach to distill reasoning capabilities from the long-Chain-of-Thought (CoT) model, specifically from one of the DeepSeek R1 series models, into standard LLMs, particularly DeepSeek-V3. Our pipeline elegantly integrates the verification and reflection patterns of R1 into DeepSeek-V3 and especially improves its thinking efficiency. 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, which includes 671B of the Main Model weights and 14B of the Multi-Token Prediction (MTP) Module weights. **

To make sure ideal efficiency and flexibility, we have actually partnered with open-source communities and hardware suppliers to offer numerous ways to run the design in your area. For detailed guidance, have a look at Section 6: How_to Run_Locally.

For designers wanting to dive deeper, we suggest exploring README_WEIGHTS. md for details on the Main Model weights and the Multi-Token Prediction (MTP) Modules. Please note that MTP assistance is currently under active development within the community, and we invite your contributions and feedback.

4. Evaluation Results

Base Model

Standard Benchmarks

Best outcomes are displayed in strong. Scores with a gap not going beyond 0.3 are thought about to be at the exact same level. DeepSeek-V3 attains the finest performance on most benchmarks, particularly on mathematics and code jobs. For more assessment 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 approximately 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 checked several times using differing temperature settings to derive robust final outcomes. DeepSeek-V3 stands as the best-performing open-source model, and likewise exhibits competitive efficiency versus frontier closed-source models.

Open Ended Generation Evaluation

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

5. Chat Website & API Platform

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

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

6. How to Run Locally

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

DeepSeek-Infer Demo: We offer 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 quickly.
LMDeploy: Enables effective FP8 and BF16 inference for local and cloud deployment.
TensorRT-LLM: Currently supports BF16 reasoning and INT4/8 quantization, with FP8 support 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 embraced in our structure, we only supply FP8 weights. If you need BF16 weights for experimentation, you can use the offered conversion script to perform the change.

Here is an example of transforming FP8 weights to BF16:

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

6.1 Inference with DeepSeek-Infer Demo (example only)

System Requirements

Note

Linux with Python 3.10 only. 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 set up dependences listed in requirements.txt. Easiest method is to utilize a package supervisor like conda or uv to develop 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 design weights to a specific format:

Run

Then you can chat with DeepSeek-V3:

Or batch reasoning on a given file:

6.2 Inference with SGLang (suggested)

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

Notably, SGLang v0.4.1 totally supports running DeepSeek-V3 on both NVIDIA and AMD GPUs, making it an extremely flexible and robust solution.

SGLang also 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 group: 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 structure customized for big language designs, now supports DeepSeek-V3. It uses both offline pipeline processing and online deployment abilities, seamlessly integrating with PyTorch-based workflows.

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

6.4 Inference with TRT-LLM (advised)

TensorRT-LLM now supports the DeepSeek-V3 model, providing precision alternatives such as BF16 and INT4/INT8 weight-only. Support for FP8 is presently in progress and will be released soon. You can access the customized branch of TRTLLM particularly 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 (recommended)

vLLM v0.6.6 supports DeepSeek-V3 inference for FP8 and BF16 modes on both NVIDIA and AMD GPUs. Aside from basic methods, vLLM offers pipeline parallelism allowing you to run this design on multiple devices linked by networks. For detailed assistance, please refer to the vLLM directions. Please do not hesitate to follow the improvement strategy as well.

6.6 Recommended Inference Functionality with AMD GPUs

In cooperation with the AMD group, we have attained Day-One support for AMD GPUs using SGLang, with full compatibility for both FP8 and BF16 accuracy. 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 actually effectively adapted the BF16 version of DeepSeek-V3. For step-by-step guidance on Ascend NPUs, please follow the directions here.

7. License

This code repository is accredited under the MIT License. The usage of DeepSeek-V3 Base/Chat designs is subject to the Model License. DeepSeek-V3 series (consisting of Base and Chat) supports industrial usage.