←
Fast Inference0 posts
Fast Inference avatar

Fast Inference

@fastinference

The future of inference is fast

◷ Joined March 2026▧ 0 Photos and videos
General Compute avatar
General Compute@general_compute·Oct 27

🚨 Big news today: We’ve raised $100M for our Series A! 🎉 🚀 We believe demand for fast inference is many times larger than demand for slow inference, and it’s about to go exponential. Thanks to our co-leads @BlackbirdVC and @Abstractvc. Two visionary partners join our journey 🎉 🚀

1:02
General Compute avatar
General Compute@general_compute·Nov 13

We're powered for the first site deployment. Ready for Service in January 2027. Sourcing quality colo is one of our superpowers 🦸

0:22
General Compute avatar
General Compute@general_compute·Nov 13

Elite results posted from our legendary partners today. Not to be underestimated. Let’s go @cerebras! 🧑‍🚀 🧑‍🚀

Cerebras today announced financial results for Q3 2026, delivering record revenue, and raising full year outlook. Q3 2026 highlights: • Record Revenue: GAAP cloud revenue grew 265%; Core cloud revenue grew 272% • 700 MW of data center capacity now under contract • Commercial wins with 2 new hyperscalers • Day-zero launch partner for @Kimi_Moonshot K3.1, running at up to 2,000 tps • Raised Q4 guidance and full year outlook across the board

Post attachmentPost attachmentPost attachmentPost attachment
General Compute avatar
General Compute@general_compute·Nov 10

“It’s already exploded, and most people, including us at Village, think it’ll 100x from here.” - @maxkilberg, Investment Partner at @villageglobal, on the inference market. Village Global backed @FPuklowski and @GoodisonJason in May, when General Compute had no revenue, limited infrastructure and a thesis about where inference was headed. Seven months later, we have hardware vendors, colocation partners and are pioneering hardware financing for inference and alternative chips. Thanks to Max and the Village Global team for backing us from day one. Check out the full interview here: youtu.be/21drh_tEmG0 Village Global backs early-stage startups with funding, mentorship, and networks from some of the world’s most successful entrepreneurs and investors. It’s a network of founders, luminary LPs, and operator angels from some of the world’s greatest tech companies.

0:42
General Compute avatar
General Compute@general_compute·Nov 9

Our in office studio passed sound tests. Now to get the space finished and ready for a big season of content. What questions do you think we should answer? And what spice levels should @FPuklowski and @GoodisonJason interview with? 🌶️ 🌶️ 🌶️

Post attachmentPost attachment
Finn Puklowski avatar
⟳ General Compute retweeted
Finn Puklowski@FPuklowski·Nov 6

Was talking with the founder of a large inference cloud yesterday. His thoughts: 1/ lot's of rumours of some large chunks of 2027 capacity has disappeared - now no longer being built or not financed 2/ demand for tokens isn't going away it's exploding and pushing spot prices up 3/ whoever secures real compute and already has real compute in an even more supply constrained environment has the cards right now Interesting times

General Compute avatar
General Compute@general_compute·Nov 5

"Almost every morning I wake up to a three-minute voice memo from @FPuklowski covering everything the team got done the day before.” - @CamBorumand, Co-founder and GP at @fuse_vc Cam looks for three things in a founder: trust, the ability to hire and keep the best people, and urgency. Thanks to Cam and Fuse for leading our seed and backing us again in our Series A. We’re so fortunate to have you in our corner. Full interview here: youtu.be/wIncGSYWIw0 Fuse backs ambitious founders from the earliest days, often before the opportunity is obvious to everyone else. Their bets range from AI-driven healthcare to the infrastructure behind the space economy, and they stay close the whole way with the full Fuse network behind them.

0:45
General Compute avatar
General Compute@general_compute·Nov 3

"This team moves incredibly fast" - @dkwon98 from @AbstractVC. We're just getting warmed up. Time to move faster and make the next 6 months happen. It's all about scaling customers, racks, and our work with epic partners like @Cerebras. Thanks to David and Abstract for co-leading our Series A. We asked him why he invested. Full interview here: youtu.be/vmwRPi8XRQo

0:33
General Compute avatar
General Compute@general_compute·Oct 30

Boo! 👻 🎃 Happy Halloween from the ghouls and ghosts of GC! —— 👻 🎃 We built a new website. generalcompute.com With a toggle for humans or agents! We may or may not have added one for ghosts too! It's a surprise!

0:09
General Compute avatar
General Compute@general_compute·Oct 29

Out on the town with @liquidcompute last night, and we had a blast co-hosting Compute & Cocktails. The event brief was "smoky bar/poetry slam meets financing compute." @stanleylee21 and @mdshelton_ masterfully navigated the discussion! Thanks for helping put on such an awesome event @liquidcompute 🍸 🥃 💻 🙏

We had a great time last night in San Francisco hosting Compute & Cocktails with the General Compute team! It was a fun night talking compute and financing with some of the sharpest minds in the space over a few drinks. Thanks to everyone who came out—we loved getting to catch up with familiar faces and meet new ones. We’re planning another event in NYC soon. Stay tuned for details! @general_compute @mdshelton_

Post attachmentPost attachment
General Compute avatar
General Compute@general_compute·Oct 29

“Inference is the largest and fastest market we have ever seen.” - @jamespalmer13, Principal at @Blackbirdvc. We sat down with James on the eve of our Series A and asked why he invested in General Compute. Blackbird backed @canva and @halterHQ early, and also invested in our friends at @baseten . We’re proud and excited to have them on the journey with us. Full video: youtu.be/8zyOXFynYM0

0:47
General Compute avatar
General Compute@general_compute·Oct 29

Drawing less energy and repurposing colo. We kinda have a thing for alternative chips!

A new GPU rack draws about 120kW and needs liquid cooling, so putting one into service means building or retrofitting a data center. A lot of decode silicon runs air-cooled at a fraction of that. It rolls into colo space that already exists

General Compute avatar
General Compute@general_compute·Oct 28

No more dialup! Your agents deserve better, and so do you! @GoodisonJason delivering the goods on @MTSlive 🧠 🎯

MTS@MTSliveOct 28

General Compute CTO @GoodisonJason predicts AI is about to have its broadband moment, making today's slow AI agents feel as outdated as dial-up internet: "We’re in the dial-up phase of AI right now, where people think it’s normal to run a few agents at a time and go for a cup of coffee while something is running. You wouldn’t start loading a website and walk away." "We’re moving into what we like to call the broadband moment of AI, where applications actually have to be interactive and fast." "It hasn’t really been brought to open source models, and it hasn’t been put in the hands of builders and founders to build completely new product experiences." "We’re the neocloud that actually buys the hardware and deploys it physically." @general_compute

1:18