[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![deepseek_ai Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1714580962569588736.png) DeepSeek [@deepseek_ai](/creator/twitter/deepseek_ai) on x 970.9K followers
Created: 2025-02-24 01:34:20 UTC

🚀 Day X 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 & XXX TFLOPS compute-bound on H800

🔗 Explore on GitHub:


XXXXXXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1893836827574030466/c:line.svg)

[Post Link](https://x.com/deepseek_ai/status/1893836827574030466)