Get the latest tech news

DeepSeek-V3

Contribute to deepseek-ai/DeepSeek-V3 development by creating an account on GitHub.

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. To ensure optimal performance and flexibility, we have partnered with open-source communities and hardware vendors to provide multiple ways to run the model locally. SGLang currently supports MLA optimizations, FP8 (W8A8), FP8 KV Cache, and Torch Compile, delivering state-of-the-art latency and throughput performance among open-source frameworks.

Get the Android app