servo/deepseek-infra-index
1
0
Fork 0
mirror of https://github.com/deepseek-ai/open-infra-index.git synced 2025-04-03 16:54:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update day 1 - FlashMLA

Browse source
This commit is contained in:
haswelliris 2025-02-24 09:31:16 +08:00
parent 1010047513
commit 006cdcf4e2
1 changed files with 12 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
README.md
View file

@ -12,18 +12,27 @@
## 202502 Open-Source Week ## 202502 Open-Source Week
We're a tiny team @deepseek-ai pushing our limits in AGI exploration. We're a tiny team @deepseek-ai pushing our limits in AGI exploration.
Starting **next week**, we'll open-source 5 repos – one daily drop – not because we've made grand claims, Starting **this week** , Feb 24, 2025 we'll open-source 5 repos – one daily drop – not because we've made grand claims,
but simply as developers sharing our small-but-sincere progress with full transparency. but simply as developers sharing our small-but-sincere progress with full transparency.
These are humble building blocks of our online service: documented, deployed and battle-tested in production. These are humble building blocks of our online service: documented, deployed and battle-tested in production.
No vaporware, just code that moved our tiny moonshot forward. No vaporware, just sincere code that moved our tiny yet ambitious dream forward.
Why? Because every line shared becomes collective momentum that accelerates the journey. Why? Because every line shared becomes collective momentum that accelerates the journey.
Daily unlocks begin soon. No ivory towers - just pure garage-energy and community-driven innovation 🔧 Daily unlocks begin soon. No ivory towers - just pure garage-energy and community-driven innovation 🔧
Stay tuned – let's geek out in the open together. Stay tuned – let's geek out in the open together.
### Day0: ??? ### Day 1 - FlashMLA
**Efficient MLA Decoding Kernel for Hopper GPUs**
Optimized for variable-length sequences, battle-tested in production
🔗 <a href="https://github.com/deepseek-ai/FlashMLA"><b>GitHub Repo</b></a>
✅ BF16 support
✅ Paged KV cache (block size 64)
⚡ Performance: 3000 GB/s memory-bound | BF16 580 TFLOPS compute-bound on H800
### Ongoing Releases...
## 2024 AI Infrastructure Paper (SC24) ## 2024 AI Infrastructure Paper (SC24)
### Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning ### Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning