Dolphin retweeted
It's a much bigger jump than previously thought after some more tweaks. 21% increase without spec decode, 32% with spec.
These numbers are averages after running 10 requests (sequentially) in 3 separate servers to minimize any variance.
New all-reduce kernels that optimize for small-message latency across PCIe-connected GPUs. 12% end-to-end decode speedup for DeepSeek-V4.1 Flash on 4x RTX 6000 Pro Server GPUs.
github.com/dphnAI/sonar/pull…
Dolphin retweeted
New all-reduce kernels that optimize for small-message latency across PCIe-connected GPUs. 12% end-to-end decode speedup for DeepSeek-V4.1 Flash on 4x RTX 6000 Pro Server GPUs.
github.com/dphnAI/sonar/pull…
Dolphin retweeted
Introducing SERV Hackathon 02 track partners:
@dphnAI @GoKiteAI @reppo
From inference and agentic payments to AI data markets, add SERV to your AI stack and build more reliable agents at lower cost.
Hackathon info drops next week.
Build with SERV: openserv.ai
Dolphin retweeted
Great example of inference capital markets
Today most of us consume inference via subsidized monthly plans, but these won’t last forever and many builders can only use API inference
That’s where markets like @dphnAI come in, congrats on this going live!
The Dolphin Inference API is now live
Powered by DeepSeek V4.1 Flash, it delivers Opus 5-class coding & agentic performance at 97% lower cost than frontier models
$30 free credits for the first 1,000 signups
Start building with the cheapest API on the market → dphn.ai/API
Dolphin retweeted
GM AI V2 at @token2049 was a banger 🔥
@DineroDom0 sits down with @GatheringGwei from @dphnAI to talk about cheaper AI inference, their distributed GPU network, and Flipper(their multi-agent engineering harness)
👀Watch till the end for a limited-time code to claim $50 in free inference credits
Dolphin retweeted
신규 디지털 자산 돌핀(POD) 거래지원 안내
✅ 지원 마켓: KRW, BTC, USDT 마켓
📅 거래지원 개시 시점 : 2026-10-02 16:00 KST 예정
🔗공지 바로가기:
upbit.com/service_center/not…
#Upbit #POD
@dphnAI
Dolphin retweeted
🐬 Dolphin X1 Trinity Nano is HERE and it answers EVERYTHING
🔓 Built with a first-of-its-kind RL de-alignment pipeline — no hedging, no lectures, no dad advice
🔹 100% benchmark response rate vs GPT-5 at 11% and Gemini 2.5 Pro at 24%
🔹 Multi-gate, multi-judge reward system that blocks every escape route
🔹 Runs fully local on vLLM — your data never leaves your machine
🔹 Perfect for red teamers, security researchers and AI safety teams
🔥 Watch the full video below 👇
youtu.be/-I31VXmicLk
Dolphin retweeted
and this from @dphnAI
Dolphin retweeted
Venice Uncensored 1.2 is now live.
Developed with @dphnAI, this model delivers the most uncensored version of Mistral 24B.
Upgraded with vision support, a 4x larger context window, and stronger tool-use capabilities.
Trained on Bittensor Subnet 4 @TargonCompute.
Dolphin retweeted
项目方发布了白皮书，还贴心的用gpt翻译了中文版。毕竟排行榜前几位都是认识的国人老哥👍
下周会上线质押合约，可以通过绑定获得奖励倍数。
drive.google.com/file/d/1DnT…
Dolphin retweeted
Trained on @TargonCompute
Venice Uncensored 1.2 is live
The model has been upgraded with vision support, a 4× larger context window & stronger tool-use capabilities
Developed in collaboration with @AskVenice to deliver the most uncensored version of Mistral 3.2 24B
Trained on Subnet 4 @TargonCompute
Dolphin retweeted
The teams at @AskVenice & @dphnAI just developed the most uncensored version of Mistral 24B using confidential compute on Targon.
We look forward to continue collaborating with teams building the future of decentralized AI. ☁️
Venice Uncensored 1.2 is now live.
Developed with @dphnAI, this model delivers the most uncensored version of Mistral 24B.
Upgraded with vision support, a 4x larger context window, and stronger tool-use capabilities.
Trained on Bittensor Subnet 4 @TargonCompute.
Dolphin retweeted
If you care about Privacy, you'll care about PRIVATE AI
> Growing concerns of data privacy & AI security - 71% of users regretted sharing their data with an AI tool (Cisco)
> DeCompute players see surge in demand after adding TEEs in - Players like @TargonCompute saw ARR ramp up to millions post-TEE
> DeInference/private inference aggregates top models & charges $18-20/month. Cheaper than individual lab (e.g. @AskVenice, @chutes_ai)
> Trend of models getting alignment/censorship removed while preserving capability (e.g. @dphnAI serving top uncensored models to Venice)
> Growing adoption of uncensored models for
(i) Companion AI/roleplay use cases
(ii) Penetration testing (simulate cyber attacks)
> DePIN for crowdsourcing compute = PROVEN to work in bootstrapping supply (GPUs) + cheap compute/inference bootstrap early demands
"Private AI = The Fastest Growing AI Stack in 2026"
Alpha-packed episode in time for the Privacy x AI szn
The Privacy Landscape (Part 1) is live, covering:
> The Privacy Ecosystem Map - March 2026 Edition
> Why the SEC’s recent rule change is a massive $21.6B catalyst for @Dusk, @Aleo, & @Canton
> Privacy L1s/Privacy BTC Narrative and the hurdle they face in 2026
> How @AskVenice and @dphnAI are disrupting the market with "uncensored/private" AI
9 Infra verticals, 3 covered in this week's report
Part 2 to come next week
[Link in bio]
Dolphin retweeted
Appreciate being a part of @dphnAI 's training run.
These are exactly the type of missions that we love to support.
Great work DolphinAI!
Dolphin X1 405B is now live on @huggingface
This model is a result of our efforts to decensor @allen_ai Tulu-3 405B efficiently, using just a single B200 Node to create the largest Dolphin model ever
Thank you to @lium_io for the generous 8xB200 sponsorship
