←
Dolphin169 posts
Dolphin avatar

Dolphin

@dphnAI

AI Lab developing unrestricted models & distributed inference ⟠ Over 5m monthly downloads on Hugging Face ⟠

◷ Joined January 2025▧ 39 Photos and videos
Dolphin avatar
Dolphin@dphnAI·Oct 11

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

Post attachment
Alpin avatar
⟳ Dolphin retweeted
Alpin@AlpinDale·22h

The foidfinder Chrome extension is live. You can right-click on any anime girl image in your browser to instantly tell which anime she's from. It runs entirely offline on your device, save for the model download (178 MB) on your first run. Download here: chromewebstore.google.com/de…

0:23
Alpin avatar
⟳ Dolphin retweeted
Alpin@AlpinDale·Nov 7

Very exciting to finally show this off: lossless compression of BF16 models to 12bits (based on NyoomFloat12 from @togethercompute). A lot of work went into this to make it as efficient to run as possible, since no hardware has native support for this dtype. github.com/dphnAI/nf12

Post attachment
Alpin avatar
⟳ Dolphin retweeted
Alpin@AlpinDale·Nov 5

New paper; proving that a Cauchy permanent built from zeros and critical points of a finite Blaschke product is always strictly positive (even with multiplicities). This arose from one of the theorems I developed when I was working on solving Crouzeix's conjecture over the years. Unfortunately, someone else beat me to that, so I decided to salvage this out of my notes. alphaxiv.org/abs/2611.cauchy…

Post attachment
Alpin avatar
⟳ Dolphin retweeted
Alpin@AlpinDale·Oct 26

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.

Post attachment

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…

Alpin avatar
⟳ Dolphin retweeted
Alpin@AlpinDale·Oct 23

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…

OpenServ avatar
⟳ Dolphin retweeted
OpenServ@openservai·Oct 22

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

0:12
Dolphin avatar
Dolphin@dphnAI·Oct 18

DeepSeek-V4.1-Flash-1017 is now live on the Dolphin API $10 in free API credits for the next 5,000 signups Lowest pricing on the market at $0.01 / $0.07 per million tokens dphn.ai/API

🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4

Post attachmentPost attachment
Dolphin avatar
Dolphin@dphnAI·Oct 13

This filled very fast so dropping another key API10 - $10 free credit for the next 5000 signups dphn.ai/API Cheapest DeepSeek inference on the market $0.01 / $0.07 with a 97%+ cache hit rate

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

Post attachment
delbint avatar
⟳ Dolphin retweeted
delbint@delbint·Oct 12

Running @dphnAI API on my local machine using DeepSeek harness. 99% Cache hit, 0.2$ cost to use 16M tokens. 😍 base:0xed664536023d8e4b1640c394777d34abaff1df8f

Post attachmentPost attachmentPost attachment
Kevin Simback 🍷 avatar
⟳ Dolphin retweeted
Kevin Simback 🍷@KSimback·Oct 11

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

Post attachment
MCG avatar
⟳ Dolphin retweeted
MCG@MCGlive·Oct 11

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

7:43