🛠 Open Source Release 🔗 Model: https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp 🔗 Tech report: https://github.com/deepseek-ai/DeepSeek-V3.2-Exp/blob/main/DeepSeek_V3_2.pdf 🔗 Key GPU kernels in TileLang & CUDA (use TileLang for rapid research prototyping!) 4/n

868 102

在 X 上查看 →

💻 API Update 🎉 Lower costs, same access! 💰 DeepSeek API prices drop 50%+, effective immediately. 🔹 For comparison testing, V3.1-Terminus remains available via a temporary API until Oct 15th, 2025, 15:59 (UTC Time). Details: https://api-docs.deepseek.com/guides/comparison_testing 🔹 Feedback welcome:

1.1K 93

在 X 上查看 →

⚡️ Efficiency Gains 🤖 DSA achieves fine-grained sparse attention with minimal impact on output quality — boosting long-context performance & reducing compute cost. 📊 Benchmarks show V3.2-Exp performs on par with V3.1-Terminus. 2/n

676 50

在 X 上查看 →

🚀 Introducing DeepSeek-V3.2-Exp — our latest experimental model! ✨ Built on V3.1-Terminus, it debuts DeepSeek Sparse Attention(DSA) for faster, more efficient training & inference on long context. 👉 Now live on App, Web, and API. 💰 API prices cut by 50%+! 1/n

6.9K 869

在 X 上查看 →

📊 DeepSeek-V3.1-Terminus delivers more stable & reliable outputs across benchmarks compared to the previous version. 👉 Available now on: App / Web / API 🔗 Open-source weights here: https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus Thanks to everyone for your feedback. It drives us to keep improving

865 67

在 X 上查看 →

🚀 DeepSeek-V3.1 → DeepSeek-V3.1-Terminus The latest update builds on V3.1’s strengths while addressing key user feedback. ✨ What’s improved? 🌐 Language consistency: fewer CN/EN mix-ups & no more random chars. 🤖 Agent upgrades: stronger Code Agent & Search Agent performance.

4.6K 512

在 X 上查看 →

Pricing Changes 💳 🔹 New pricing starts & off-peak discounts end at Sep 5th, 2025, 16:00 (UTC Time) 🔹 Until then, APIs follow current pricing 📝 Pricing page: https://api-docs.deepseek.com/quick_start/pricing/ 5/5

930 56

在 X 上查看 →

Model Update 🤖 🔹 V3.1 Base: 840B tokens continued pretraining for long context extension on top of V3 🔹 Tokenizer & chat template updated — new tokenizer config: https://huggingface.co/deepseek-ai/DeepSeek-V3.1/blob/main/tokenizer_config.json 🔗 V3.1 Base Open-source weights: https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base 🔗 V3.1 Open-source weights:

865 45

在 X 上查看 →

Tools & Agents Upgrades 🧰 📈 Better results on SWE / Terminal-Bench 🔍 Stronger multi-step reasoning for complex search tasks ⚡️ Big gains in thinking efficiency 3/5

807 47

在 X 上查看 →

API Update ⚙️ 🔹 deepseek-chat → non-thinking mode 🔹 deepseek-reasoner → thinking mode 🧵 128K context for both 🔌 Anthropic API format supported: https://api-docs.deepseek.com/guides/anthropic_api ✅ Strict Function Calling supported in Beta API: https://api-docs.deepseek.com/guides/function_calling 🚀 More API resources, smoother

790 40

在 X 上查看 →

Introducing DeepSeek-V3.1: our first step toward the agent era! 🚀 🧠 Hybrid inference: Think & Non-Think — one model, two modes ⚡️ Faster thinking: DeepSeek-V3.1-Think reaches answers in less time vs. DeepSeek-R1-0528 🛠️ Stronger agent skills: Post-training boosts tool use and

14.7K 1.7K

在 X 上查看 →

🚀 DeepSeek-R1-0528 is here! 🔹 Improved benchmark performance 🔹 Enhanced front-end capabilities 🔹 Reduced hallucinations 🔹 Supports JSON output & function calling ✅ Try it now: https://chat.deepseek.com/ 🔌 No change to API usage — docs here: https://api-docs.deepseek.com/guides/reasoning_model 🔗

9.6K 1.5K

在 X 上查看 →

🚀 DeepSeek-V3-0324 is out now! 🔹 Major boost in reasoning performance 🔹 Stronger front-end development skills 🔹 Smarter tool-use capabilities ✅ For non-complex reasoning tasks, we recommend using V3 — just turn off “DeepThink” 🔌 API usage remains unchanged 📜 Models are

11.6K 1.9K

在 X 上查看 →

🚀 Day 6 of #OpenSourceWeek: One More Thing – DeepSeek-V3/R1 Inference System Overview Optimized throughput and latency via: 🔧 Cross-node EP-powered batch scaling 🔄 Computation-communication overlap ⚖️ Load balancing Statistics of DeepSeek's Online Service: ⚡ 73.7k/14.8k

9K 1.2K

在 X 上查看 →

🚀 Day 5 of #OpenSourceWeek: 3FS, Thruster for All DeepSeek Data Access Fire-Flyer File System (3FS) - a parallel file system that utilizes the full bandwidth of modern SSDs and RDMA networks. ⚡ 6.6 TiB/s aggregate read throughput in a 180-node cluster ⚡ 3.66 TiB/min

10.1K 1.2K

在 X 上查看 →

🚀 Day 4 of #OpenSourceWeek: Optimized Parallelism Strategies ✅ DualPipe - a bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training. 🔗 https://github.com/deepseek-ai/DualPipe ✅ EPLB - an expert-parallel load balancer for V3/R1. 🔗

5.8K 786

在 X 上查看 →

🚨 Off-Peak Discounts Alert! Starting today, enjoy off-peak discounts on the DeepSeek API Platform from 16:30–00:30 UTC daily: 🔹 DeepSeek-V3 at 50% off 🔹 DeepSeek-R1 at a massive 75% off Maximize your resources smarter — save more during these high-value hours!

6.6K 616

在 X 上查看 →

🚀 Day 3 of #OpenSourceWeek: DeepGEMM Introducing DeepGEMM - an FP8 GEMM library that supports both dense and MoE GEMMs, powering V3/R1 training and inference. ⚡ Up to 1350+ FP8 TFLOPS on Hopper GPUs ✅ No heavy dependency, as clean as a tutorial ✅ Fully Just-In-Time compiled

6.3K 851

在 X 上查看 →

🚀 Day 2 of #OpenSourceWeek: DeepEP Excited to introduce DeepEP - the first open-source EP communication library for MoE model training and inference. ✅ Efficient and optimized all-to-all communication ✅ Both intranode and internode support with NVLink and RDMA ✅

8K 1K

在 X 上查看 →

🚀 Day 1 of #OpenSourceWeek: FlashMLA Honored to share FlashMLA - our efficient MLA decoding kernel for Hopper GPUs, optimized for variable-length sequences and now in production. ✅ BF16 support ✅ Paged KV cache (block size 64) ⚡ 3000 GB/s memory-bound & 580 TFLOPS

10.1K 1.3K

在 X 上查看 →

🚀 Day 0: Warming up for #OpenSourceWeek! We're a tiny team @deepseek_ai exploring AGI. Starting next week, we'll be open-sourcing 5 repos, sharing our small but sincere progress with full transparency. These humble building blocks in our online service have been documented,

20.3K 2.5K

在 X 上查看 →

🚀 Introducing NSA: A Hardware-Aligned and Natively Trainable Sparse Attention mechanism for ultra-fast long-context training & inference! Core components of NSA: • Dynamic hierarchical sparse strategy • Coarse-grained token compression • Fine-grained token selection 💡 With

15.2K 2.1K

在 X 上查看 →

🎉 Excited to see everyone’s enthusiasm for deploying DeepSeek-R1! Here are our recommended settings for the best experience: • No system prompt • Temperature: 0.6 • Official prompts for search & file upload: http://bit.ly/4hyH8np • Guidelines to mitigate model bypass

15.5K 1.6K

在 X 上查看 →

📢 Terminology Correction: DeepSeek-R1’s code and models are released under the MIT License.

869 69

在 X 上查看 →