Overview

  • Founded Date July 24, 2020
  • Sectors مخازن
  • Posted Jobs 0
  • Viewed 5

Company Description

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 achieve efficient inference and economical training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly confirmed in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger efficiency. We pre-train DeepSeek-V3 on 14.8 trillion diverse and premium tokens, followed by Supervised Fine-Tuning and Reinforcement Learning phases to fully harness its abilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and accomplishes efficiency similar to leading closed-source models. Despite its exceptional performance, DeepSeek-V3 needs just 2.788 M H800 GPU hours for its complete training. In addition, its training procedure is incredibly stable. 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 technique for load balancing, which decreases the performance deterioration that occurs from motivating load balancing.
– We examine a Multi-Token Prediction (MTP) objective and prove it beneficial to model efficiency. It can also be utilized for speculative decoding for reasoning acceleration.

Pre-Training: Towards Ultimate Training Efficiency

– We create an FP8 mixed accuracy training structure and, for the first time, confirm the expediency and efficiency of FP8 training on an incredibly massive model.
– Through co-design of algorithms, structures, and hardware, we overcome the communication traffic jam in cross-node MoE training, nearly attaining complete computation-communication overlap.
This substantially boosts our training performance and reduces the training costs, allowing us to even more scale up the design size without additional overhead.
– At an affordable expense of only 2.664 M H800 GPU hours, we complete the pre-training of DeepSeek-V3 on 14.8 T tokens, producing the currently greatest open-source base design. The subsequent training stages after pre-training require just 0.1 M GPU hours.

Post-Training: Knowledge Distillation from DeepSeek-R1

– We introduce an ingenious approach to distill reasoning capabilities from the long-Chain-of-Thought (CoT) design, particularly from one of the DeepSeek R1 series designs, into standard LLMs, especially DeepSeek-V3. Our pipeline elegantly incorporates the verification and reflection patterns of R1 into DeepSeek-V3 and especially enhances its reasoning efficiency. Meanwhile, we also preserve a control over the output style and length of DeepSeek-V3.

3. Model Downloads

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

To guarantee optimum efficiency and versatility, we have partnered with open-source neighborhoods and hardware suppliers to provide numerous ways to run the model in your area. For step-by-step guidance, take a look at Section 6: How_to Run_Locally.

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

4. Evaluation Results

Base Model

Standard Benchmarks

Best outcomes are revealed in strong. Scores with a gap not surpassing 0.3 are considered to be at the same level. DeepSeek-V3 achieves the very best efficiency on a lot of criteria, particularly on math and code tasks. For more examination details, please examine our paper.

Context Window

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

Chat Model

Standard Benchmarks (Models bigger than 67B)

All designs are evaluated in a configuration that restricts the output length to 8K. Benchmarks containing less than 1000 samples are tested numerous times using varying temperature level settings to obtain robust results. DeepSeek-V3 stands as the best-performing open-source design, and likewise displays competitive efficiency against frontier closed-source models.

Open Ended Generation Evaluation

English open-ended discussion assessments. 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 main website: chat.deepseek.com

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

6. How to Run Locally

DeepSeek-V3 can be released in your area utilizing the following hardware and open-source neighborhood software:

DeepSeek-Infer Demo: We provide a basic and light-weight demo for FP8 and BF16 reasoning.
SGLang: Fully support the DeepSeek-V3 model in both BF16 and FP8 reasoning modes, with Multi-Token Prediction coming quickly.
LMDeploy: Enables effective FP8 and BF16 reasoning for regional and cloud release.
TensorRT-LLM: Currently supports BF16 reasoning and INT4/8 quantization, with FP8 support coming soon.
vLLM: Support DeepSeek-V3 model 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 supply FP8 weights. If you need BF16 weights for experimentation, you can utilize the offered conversion script to carry out 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 set up dependences listed in requirements.txt. Easiest way is to utilize a bundle supervisor like conda or uv to produce a brand-new virtual environment and set up the dependences.

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 particular format:

Run

Then you can chat with DeepSeek-V3:

Or batch inference 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 state-of-the-art latency and throughput efficiency amongst open-source structures.

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

SGLang also supports multi-node tensor parallelism, allowing you to run this design on multiple network-connected machines.

Multi-Token Prediction (MTP) is in development, 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 (advised)

LMDeploy, a versatile and high-performance reasoning and serving structure customized for large language models, now supports DeepSeek-V3. It offers both offline pipeline processing and online implementation abilities, seamlessly integrating with PyTorch-based workflows.

For extensive detailed guidelines 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, providing accuracy alternatives such as BF16 and INT4/INT8 weight-only. Support for FP8 is presently in development and will be released soon. 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/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 basic methods, vLLM provides pipeline parallelism enabling you to run this model on several devices linked by networks. For detailed guidance, please refer to the vLLM instructions. Please feel complimentary to follow the improvement plan also.

6.6 Recommended Inference Functionality with AMD GPUs

In partnership with the AMD group, we have actually attained Day-One assistance for AMD GPUs using SGLang, with full compatibility for both FP8 and BF16 precision. For detailed assistance, please describe the SGLang guidelines.

6.7 Recommended Inference Functionality with Huawei Ascend NPUs

The MindIE structure from the Huawei Ascend neighborhood has actually successfully adapted the BF16 version of DeepSeek-V3. For step-by-step guidance on Ascend NPUs, please follow the guidelines here.

7. License

This code repository is accredited under the MIT License. Making use of DeepSeek-V3 Base/Chat designs undergoes the Model License. DeepSeek-V3 series (consisting of Base and Chat) supports commercial usage.