Outerport retweeted
スケルトンゲームボーイ的な筐体の中で、プリント基板上で動くプラントシミュレータのおもちゃを弊社システムで一気通貫でやらせてみた
こちらは実際に製作してみて弊社の記念品として用意する予定です・・・
Outerport retweeted
ダイキン工業様との協業を発表しました!設計でのAI活用において、必要なノウハウが詰まっている図形・図表を構造化するOuterportの技術を本格導入していただきました。
CG/CV/AIの技術を総動員して、新たなハードウェア技術の設計・開発・製造がもっと速くできる世界を目指して精進いたします🛠️🏭⚙️
Outerport retweeted
ダイキン工業、AIによる図表・図面の「構造化」プラットフォームとしてOuterportを導入し、AIエージェント活用を推進 prtimes.jp/main/html/rd/p/00…
Outerport retweeted
Parsing CAD drawings is one thing but parsing architectural plans takes the craziness up a notch
Outerport retweeted
Yeah document parsing is cool, but what about CAD drawing parsing... (but with documents too 🥺)
Outerport retweeted
My little prediction of 2025: As AI scaling is plateauing (steady amazing progress like microprocessors vs jumps), we'll begin to see more of a focus on products.
Instead of a multi-modal architecture, there will be a focus on a multi-model architectures: how do we jointly train and integrate the AI models to work together to maximize perf while updating the models quickly.
I would expect to see every major industry get targeted (already happening): AI graphic designer, AI programmer, AI lawyer, AI doctor, AI chip designer, AI FP&A, etc.
The AI labs will have to cut burn and finally ask themselves: who is this for? why do they want it?
Outerport retweeted
.@outerport is building the infrastructure base for multi-model architectures; figuring out the technical details like hot-swapping, time multiplexing, live-deployments, kv cache management, and more 😉
My little prediction of 2025: As AI scaling is plateauing (steady amazing progress like microprocessors vs jumps), we'll begin to see more of a focus on products.
Instead of a multi-modal architecture, there will be a focus on a multi-model architectures: how do we jointly train and integrate the AI models to work together to maximize perf while updating the models quickly.
I would expect to see every major industry get targeted (already happening): AI graphic designer, AI programmer, AI lawyer, AI doctor, AI chip designer, AI FP&A, etc.
The AI labs will have to cut burn and finally ask themselves: who is this for? why do they want it?
Outerport retweeted
How do you hide latency for loading models from disk?
Most implementations do disk -> CPU RAM, and then a CPU RAM -> GPU RAM sequentially. The latency of loading into the GPU is the sum of the two steps.
In practice, these 2 steps can actually be interlaced because a model weight is not a blob of memory and is actually a collection of tensors.
We can hide the latency of the model load by parallelizing disk->RAM and the RAM->GPU by processing these two tasks in 2 different thread pools that communicate to each other with a channel queue that sends over tensors.
One pool of threads will load memory pages and mark named tensors as complete when all pages have loaded, and push the tensor onto the queue. Another thread will take in completed tensors and start the transfer into GPU for that tensor.
In a naive implementation this would actually be very slow since each tensor can be small and opening up a CUDA context and kernel for each named tensor would create large amounts of overhead. So, we also need to do buffering so that there is a sufficiently large set of tensors that are marked complete before a batched write to GPU happens. (We experimentally determined 64MB pages are pretty good 🙂)
As a result the bottleneck ends up being almost entirely the "disk to RAM" step- because the RAM to GPU is comparatively fast and can be parallelized.
Outerport retweeted
弊社(@Outerport)がニューヨークでタイムズスクエアデビューしました!
Outerport retweeted
2️⃣ Developer tools and automation are hot
26% of the AI startups are building scaffolding for the next tech boom, making it faster & easier to build better AI applications.
@keetapi: APIs for any website
@outerport: VMWare for GPUs
@mem0ai: Memory layer for AI agents
+48 more
Outerport retweeted
.@outerport This feels like it should already exist, but I don't know a company that does exactly what they are doing
Outerport retweeted
Meet Outerport 🔥🔥
A model weight registry with a Python API for efficient AI model management across distributed servers. It offers:
1. Performance: Fast downloads and multi-level caching for quick model swapping.
2. Reliability: No single point of failure, self-hosting option.
3. Security: Optional encryption and access logging.
4. Scalability: Fast horizontal scaling with predictive scheduling.
Built on Rust, it uses model compression and low-level GPU programming.
Their hotswapping reduces GPU costs by 40% for multi-model services. It allows Spinning up/down different models on a single GPU node to manage variable demand , Loading models onto GPUs only when needed and Utilizing GPU resources for other tasks during low-traffic periods.
Live demo link in 🧵
Outerport retweeted
Cool to see so many YC companies launching with a @Gradio demo. Who needs a pitch deck anymore??
Kudos @outerport on the launch 🚀
Outerport retweeted
「LLMのAPIに依存するリスクとは」
ビジネスの要として第三者のAPIを使ってしまうと、障害が起きたときに対処できなくなってしまいます。実際、昨日の夜、Claudeの画像APIが一時的にダウンし、その影響で一時的に運営が停止したスタートアップがいくつかあったようです。
このようなリスクを回避するため、アウターベイシス(@outerbasis)は自社でLLMや生成AI技術を効率よく運用するためのソフトウェアの開発に取り組んでいます!
This quoted post is unavailable.
Outerport retweeted
Third-party APIs for LLMs and generative AI are risky because when they go down, there's not much you can do- and that's why we're building self-hosted solutions to run generative AI deployments on your own managed cloud.
@outerbasis lets companies prepare infrastructure for multiple heterogenous services running different kinds of models, so that you can handle unpredictable demands & context switch for different tasks. Check out this live demo!
This quoted post is unavailable.





















