Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Our heterogeneous cloud just got better. We're announcing a cluster scale deployment of Positron AI as our next partner. We believe demand for fast inference will outstrip supply for the next decade. Our bet on Positron is another step towards getting fast inference for opensource models into builders' hands....

467,236 Aufrufe • vor 28 Tagen •via X (Twitter)

44 Kommentare

Profilbild von litquidity
litquidityvor 28 Tagen

@positron_ai The building will continue unabated

Profilbild von General Compute
General Computevor 28 Tagen

@positron_ai

Profilbild von Finn Puklowski
Finn Puklowskivor 28 Tagen

@positron_ai LFG ! Proud to be partnering with @mitesh711 and @trsohmers to get more fast inference into developers' + builders' hands.

Profilbild von HOW THINGS WORK
HOW THINGS WORKvor 28 Tagen

@positron_ai Its all about the speed! Excited for this one

Profilbild von General Compute
General Computevor 28 Tagen

@positron_ai Fitting! ⚡️

Profilbild von Shay Boloor
Shay Boloorvor 28 Tagen

@positron_ai AI agents are going to drive so much more inference demand.

Profilbild von Paul Mit
Paul Mitvor 28 Tagen

@positron_ai Well That sounds very serious Congrats

Profilbild von Not Elon Musk
Not Elon Muskvor 28 Tagen

@positron_ai This is how we push SI/AI forward 🔥🔥🔥

Profilbild von General Compute
General Computevor 28 Tagen

@positron_ai

Profilbild von Parul Gautam
Parul Gautamvor 28 Tagen

@positron_ai Big step toward making fast inference more accessible. Exciting to see this partnership focused on open-source models!

Profilbild von Rohan Paul
Rohan Paulvor 28 Tagen

@positron_ai wow, so many innovations cominng the inference space. prefill on GPUs and decode on memory-first chips is exactly what agent era needs

Profilbild von Atul Kumar
Atul Kumarvor 28 Tagen

@positron_ai Open-source AI needs serious compute behind it. This partnership could unlock something huge..

Profilbild von elvis
elvisvor 28 Tagen

@positron_ai This signals a major shift in AI infrastructure and compute needs. Very excited to see this partnership meet those demands. Also, @mitesh711 is killing it. :)

Profilbild von General Compute
General Computevor 28 Tagen

@positron_ai @mitesh711 @FPuklowski and @GoodisonJason are huge fans of @mitesh711 and the team! 🫶

Profilbild von Ronin
Roninvor 28 Tagen

@positron_ai Since saas is overloaded, probably inference is one of not many good options

Profilbild von Markets & Mayhem
Markets & Mayhemvor 28 Tagen

@positron_ai This is an incredibly exciting collaboration. Congratulations to both @general_compute and @positron_ai! I'd love to experience this new cluster when it comes online. 🦾

Profilbild von Eon.io
Eon.iovor 28 Tagen

@positron_ai LETS GOOOO!

Profilbild von Markandey Sharma
Markandey Sharmavor 28 Tagen

@positron_ai Q1 2027 will be an interesting milestone for this partnership.

Profilbild von Aman
Amanvor 28 Tagen

@positron_ai specialized chips for inference are definitely worth watching

Profilbild von The Rabbit Hole
The Rabbit Holevor 28 Tagen

@positron_ai Gotta go fast

Profilbild von Muhammad Ayan
Muhammad Ayanvor 28 Tagen

@positron_ai Alright, LFG 🔥

Profilbild von pika capital
pika capitalvor 28 Tagen

@positron_ai The agentic economy is going to require so much more. LETS GO!!!

Profilbild von Utkarsh Sharma
Utkarsh Sharmavor 28 Tagen

@positron_ai Great to see more partnerships focused on scaling open-source AI.

Profilbild von Santiago
Santiagovor 28 Tagen

@positron_ai Quick question: do you have any benchmarks on how long it takes to move the KV cache to different hardware?

Profilbild von Patrick P. L. Tsang
Patrick P. L. Tsangvor 28 Tagen

@positron_ai AI demand is not the question anymore The opportunity is in delivering more useful compute from every dollar of infrastructure already deployed

Profilbild von shirish
shirishvor 28 Tagen

@positron_ai which open-source models are you guys putting on the cluster first

Profilbild von JUNK BOND ANALYST 👻
JUNK BOND ANALYST 👻vor 28 Tagen

@positron_ai

Profilbild von General Compute
General Computevor 28 Tagen

@positron_ai We're stoked to bring @positron_ai on as a partner!

Profilbild von JUNK BOND ANALYST 👻
JUNK BOND ANALYST 👻vor 28 Tagen

@positron_ai

Profilbild von Aaliya
Aaliyavor 28 Tagen

@positron_ai Great to see another step toward faster AI model replies.

Profilbild von Liam | AI Tools & News
Liam | AI Tools & Newsvor 28 Tagen

@positron_ai The one contract part matters too. Builders shouldn't have to manage two hardware setups just to split prefill and decode.

Profilbild von Henry Zheng
Henry Zhengvor 28 Tagen

@positron_ai Very cool!

Profilbild von Alex | AI Shortcut
Alex | AI Shortcutvor 28 Tagen

@positron_ai gemini’s long-context mode already separates prefill cost from decode in the API billing, so you can see the same split today without waiting for new chips. the difference is you still pay for the memory bandwidth either way

Profilbild von Wall St Engine
Wall St Enginevor 28 Tagen

@positron_ai MORE INFERENCE!

Profilbild von K2S
K2Svor 28 Tagen

@positron_ai can u pick what runs on positron or its all one endpoint

Profilbild von Peng
Pengvor 28 Tagen

@positron_ai So the slow part was memory the whole time That changes how I think about inference speed

Profilbild von Sachin Kumar
Sachin Kumarvor 28 Tagen

@positron_ai Fast inference is about to be the new GPU shortage. Smart move adding Positron

Profilbild von General Compute
General Computevor 28 Tagen

@positron_ai Totally agree. Silicon is going to be worth more than gold soon enough!

Profilbild von Anatoli Kopadze
Anatoli Kopadzevor 28 Tagen

@positron_ai congrats on the partnership, this one makes a lot of sense

Profilbild von General Compute
General Computevor 28 Tagen

@positron_ai Thanks, we're stoked with this one too! @positron_ai 🙏

Profilbild von Documenting AGI
Documenting AGIvor 28 Tagen

@positron_ai Love seeing more options for fast decode. Agents need this.

Profilbild von General Compute
General Computevor 28 Tagen

@positron_ai We're building an awesome selection of options!

Profilbild von Kaif
Kaifvor 28 Tagen

@positron_ai This makes total sense to me as a developer

Profilbild von Adarsh Chetan
Adarsh Chetanvor 28 Tagen

@positron_ai LFG! 🚀 More compute for open-source models means faster inference and more innovation for builders!

Ähnliche Videos