Pedro Gengo 🐉 @Predogl
research @runwayml github.com/pedrogengo São Paulo, Brazil Joined December 2010-
Tweets327
-
Followers486
-
Following481
-
Likes746
I was fascinated when I first heard about kernel fusion from @cHHillee's blog post "Making Deep Learning Go Brrrr From First Principles" (yes, I am a big fan of this post). I am still a novice in kernel programming so could not build a fused kernel myself. The `kernels` project from @huggingface came to the rescue. I could choose from the 100s of kernels on the Hub and profile it. In the blog, we use the GeGLU FFN fused Liger kernel, and the profile is beautiful. 🤩
It is profiling time! ⏰ In Part 2 we cover: > trace a Linear layer > talk about mul + add vs linear > gemm epilogues (my favourite part) > trace MLP > torch compile vs liger kernels > use hugging face kernels Bookmark this for a fun weekend read! 😎
Link to post huggingface.co/blog/torch-mlp… Thanks to @remi_or_ @SergioPaniego @RisingSayak @pcuenq for their vital reviews, and also @NoeFlandre and @Predogl for their reviews in the initial draft. Thanks for being critical and supportive of the effort. 🤗
Last chance to RSVP for our annual CVPR Friends Dinner in Denver on June 4th for conversation, cocktails and bites. RSVP at the link below.
"Otterly Lost" is a short film 100% generated by AI, based on prompting by me, Fabrício Carraro. This project is an experiment in pushing the boundaries of generative storytelling by leveraging modern AI workflows, which tells the story of Ollie, a river otter who's lost his favorite rock, and Pippa, his unamused otter wife. Every element of this short was generated using the following tools: - Video & Voice Generation: Produced entirely on @runwayml, using the Seedance 2.0 video model. - Background music: Generated on @ElevenLabs. - Sony Vegas for editing the generated chunks and music together.
Aleph 2.0 is here. Now you can edit a single frame in your video, preview the change and then Aleph 2.0 carries that edit across the rest of your video. Try it now in the new Edit Studio on web at the link below.
Today we're announcing Runway's expansion into Japan: we're opening a Tokyo office and investing an initial $40M in the country, as we build on what is already one of our largest and fastest-growing markets. We've tripled our enterprise customer base in the country in the last 12 months, with Japan becoming our third largest market globally. Companies like Yamaha, NHN and SoftBank are adopting Runway across marketing, advertising and creative content, and this expansion brings us closer to Japan's leading companies in gaming, media and robotics. Learn more about the initiative and the roles we're hiring for at the link below.
ICYMI: Over the past two weeks, we've published a series of in-depth looks into how we deploy frontier video and world models into production, across engineering, research, and trust and safety. From how we optimized GWM-1 to serve Characters (which I believe is one of the largest deployments of real-time autoregressive diffusion today), to reducing cold start times by 60x for our inference workers via GPU-to-GPU transfer of model weights, to open-sourcing our configuration system for training and evaluation configs, and finally, the continuous work we do to ensure child safety across our platforms. There are a lot of novel challenges we face as Runway increasingly becomes the world's infrastructure for generating pixels, media, and worlds, and we'll start sharing more of the behind-the-scenes in the weeks and months ahead.
Runway added more than $40M in net new ARR so far this quarter, and we're less than halfway through. The biggest growth period in the history of the company. Generative video has hit its inflection point. Enterprises like Amazon and Robinhood are using Runway daily to reshape how they tell stories and reach customers, on our frontier video and world models. Thank you to our team and our customers. The best is yet to come.
runway characters represents an important step forward in research: real time video gen that feels smooth, natural, and yet still consistent. Super proud of the team and this amazing accomplishment!
Introducing, Runway Characters. Real-time intelligent avatars that turn the internet into a conversation. Deployable anywhere via the Runway API, Runway Characters can be customized in any way across every style. All with the ability to embed bespoke knowledge banks, custom
Introducing, Runway Characters. Real-time intelligent avatars that turn the internet into a conversation. Deployable anywhere via the Runway API, Runway Characters can be customized in any way across every style. All with the ability to embed bespoke knowledge banks, custom voices and instructions. Start integrating Runway Characters directly into your apps, websites, products and services today. Available now at the link below.
We showed 1,000 people a series of videos. Some real and some generated with Gen-4.5. Over 90% of people couldn't tell the difference. Can you? Take the test at the link below.
Introducing Image to Video for Gen-4.5, the world's best video model. Built for longer stories. Precise camera control. Coherent narratives. And characters that stay consistent. Gen-4.5 Image to Video is available now for all paid plans.
Introducing our new frontier video model, Runway Gen-4.5. Previously known as Whisper Thunder (aka) David. Gen-4.5 is state-of-the-art and sets a new standard for video generation motion quality, prompt adherence and visual fidelity. Learn more below.
Reframe is here. Outpaint and resize any uploaded video, image, or #DreamMachine creation into every format you need. Customize and reposition freely on the canvas to make every version of your story fit perfectly. Goodbye cropping. Hello creative freedom.
@ariG23498 @karpathy @lusxvr @andimarafioti Amazing (as always)!!!
Introducing A Branding New ComfyUI Look and Native API Nodes! Seamlessly integrate 11 amazing online visual AI models into ComfyUI, including @bfl_ml Flux, @Hailuo_AI, @minimax_ai, @Kling_ai, @LumaLabsAI, @PixVerse_, @recraftai, @StabilityAI, @Google Veo2, @ideogram_ai, @OpenAI GPT image-1, and @pika_labs! 🔹One platform, 11 models, 65 nodes, all at once 🔹Chain the APIs with open models and workflows 🔹No hardware limitation!
Introducing #Ray2 Camera Motion Concepts in #DreamMachine — 20+ precision-tuned camera motions designed for smooth cinematic control and great reliability. Concepts compose with each other making hundreds of impossible new camera moves possible. Available now.
Ray2 Flash is now available in API.
sagnik pramanik @Sagnikkkkkkkkk
526 Followers 550 Following ml & mlops engineer | fde @ sync. labs (YC W24)
Rafael Alves @Rafaellimagtr
16 Followers 460 Following
Aman @beingamanFF
510 Followers 927 Following Multimodal Generalist, DS @HiLabs_inc | GSoC ’26 @GNUOctave | IIT Roorkee alum | Explaining SOTA DL & systems | Constantly building, lifting, running.
Anastasis Germanidis @agermanidis
5K Followers 447 Following Simple ideas, pursued maximally. Co-Founder & Co-CEO @runwayml.
Gustavo De Mari Perei... @guhdemari
456 Followers 6K Following machine learning, data science, software engineering
Donghoon Ahn @ ICML @donghoon_ahn
363 Followers 656 Following PhD student @berkeley_ai | Internship @reve, @kaist_ai | B.S. Korea University CS&E https://t.co/wD95R34SCh Generative models in the vision domain
JesseNumonic @JesseNumonic
0 Followers 25 Following
anddoom @anddoom12s
14 Followers 211 Following
André Faria Gomes @andrefaria
2K Followers 3K Following CEO @ bluesoftbr | Board Advisor | Angel Investor | 25+ Years Scaling B2B SaaS | Helping Retail Thrive with Technology 🚀
AFilho @ArlirioM
20 Followers 1K Following
Geneilton @Geneilton1
609 Followers 623 Following Sonhador de causas possíveis, eterno aprendiz da vida. Não tenho todas as respostas, mas estou vivendo e aprendendo a cada dia para alcançá-las.
Mario de Sousa Lima @MarioSousaLima
117 Followers 7K Following
Osmirio Neto @OsmirioNeto
270 Followers 2K Following
Elifelete @Elifelete14
63 Followers 2K Following Tech | Innovation | Marketing | Business — Fullstacking life with AI
Vanilla Ninja @estvanilla
0 Followers 6K Following
Igor natan @Igoornt
8 Followers 397 Following
Thiego Carvalho @thibuenosaires
105 Followers 349 Following
. @k234hj54u673gt
50 Followers 611 Following
Jones Lauriano @JonesLauriano
2K Followers 7K Following 📈📊☕🏆 Dados: 🎯 Prediction markets: 🟩🟩🟩🟩🟩🟩 Pai/Dad: 🟩🟩🟩🟩🟩🟩 Esposo/Spouse: 🟩 Irmão/brothers: 🟩🟩🟩 Anticomunista e Antifeminista ✝
Umberto Vicari @umbertovicari
0 Followers 955 Following
Leonardo Brito @lbrito_sl
1K Followers 192 Following
Henrique @henriquerabisco
40 Followers 1K Following
Rodrigo Terron → LO... @rodrigoterron
15K Followers 9K Following Forbes U30 | MIT Innovators U35 | Exit ’21 | VC https://t.co/hmxBwF85Aw | Helping founders at NewHack | Gaming & esports investor @losgrandesgg 🚀 #BuildInPublic
Yan Goes @yangoestoso
48 Followers 497 Following - linda, louca, fã do jamiroquai e faço presença vip na casa dos meus pais - tudo é política -
aiplague @aiplague
1K Followers 474 Following Creative Technologist at @silverside_AI | Exploring and shaping new visual forms through generative AI.
Esmeralda @Kumqea926297
229 Followers 7K Following If you’re going to be two-faced, at least make one of them pretty.
Nadav Timor @NadavTimor
1K Followers 8K Following AI inference, speculative decoding, open source. Built novel decoding algorithms – default in Hugging Face Transformers (160+ ⭐). Making AI faster + cheaper
jm @jm_silva44
944 Followers 665 Following sonha e serás livre de espírito, luta e serás livre na vida
Florian Wenzel @flwenz
1K Followers 2K Following I share takes on GenAI research and building a startup. CTO/cofounder @MireloAI: building foundation models for music/sound. Ex @GoogleDeepMind, @AWSAI.
Osvaldo R. Rissetti @osvaldorissetti
27 Followers 146 Following Good guy, investor, love to travel around...
Besher @mr_besher
48 Followers 714 Following
Marie @878U2MDtlSiBLq
27 Followers 894 Following
ML Developer Programs @ml_ecosystem
35 Followers 312 Following
Eula Franey @EulaFraney59644
89 Followers 3K Following
Keegan McCallum @keeganmccallum3
111 Followers 72 Following Building inference infrastructure for the interactive era https://t.co/mplYRTIvai 🟢
Jon Finger @mrjonfinger
25K Followers 726 Following Creative Workflow Executive @LumaLabsAi @dreamlabla
Confident Security @confident_sec
118 Followers 483 Following Provably private, secure, and compliant AI inference engine. Ask us anything about AI privacy!
Bets, Math, & Beyond @Pok3rBrok3rs
140 Followers 2K Following 2025 Founded Sports Betting advisory and analytics co.
341q5 @341q5
353 Followers 4K Following
nei @uiiaiuiiaiui
147 Followers 3K Following
Omar Sanseviero @osanseviero
71K Followers 3K Following MTS at @GoogleDeepMind Building Gemini, Gemma, AI Studio and more. My views ex-Chief Llama Officer @huggingface 🇵🇪🇲🇽
Suraj Patil @psuraj28
6K Followers 67 Following crafting pixels in the forest @bfl_ai prev: Research Engineer @pika_labs, Open Source AI @huggingface. Co-created diffusers 🧨
Pollen Robotics @pollenrobotics
9K Followers 222 Following Building open source robots made by open minded humans to explore real-world applications. @Huggingface family Join our community: https://t.co/KFG0LopcZt
Dwarkesh Patel @dwarkesh_sp
239K Followers 1K Following Host of @dwarkeshpodcast https://t.co/3SXlu7fy6N https://t.co/4DPAxODFYi https://t.co/hQfIWdM1Un
Nathan Lambert @natolambert
90K Followers 917 Following Open model research @ something new. Prev. co-led Olmo at Ai2. Contact via email. Writes @interconnectsai Wrote The RLHF Book, 🏔️🏃♂️
Yan Goes @yangoestoso
48 Followers 497 Following - linda, louca, fã do jamiroquai e faço presença vip na casa dos meus pais - tudo é política -
NVIDIA AI Developer @NVIDIAAIDev
112K Followers 387 Following This account is inactive. Follow @NVIDIAAI for the latest updates.
LTX.io @ltx_io
37K Followers 49 Following An open-source AI creative engine for real production. Native 4K fidelity, built for enterprise, developers, and studios.
Matt Krzus @mattkrzus
104 Followers 2K Following research enjoyoor. jiu jitsu black belt. roadhouse is the greatest movie ever made.
Nicolas Neubert @iamneubert
60K Followers 513 Following ✦ Creative Principal / Manager at @runwayml. ✦ Work recognized by Forbes, The New York Times, Bloomberg & CNN.
Kling AI @Kling_ai
134K Followers 539 Following Join KLING AI Community💫 Discord:https://t.co/kUVSFwBlEu TikTok:https://t.co/J7oMx5kPxn IG:https://t.co/DDAKgGvLqh
Neil Zeghidour @neilzegh
6K Followers 772 Following CEO @GradiumAI. Founder of @kyutai_labs. Invented neural codecs and audio LLMs. Prev. Google DeepMind/Brain, Meta, Toha Heavy Industries.
Joel Kwartler @JoelKwartler
827 Followers 3K Following Face for radio, voice for print, body for swimsuit modeling. Lead product @runwayml, @botnikstudios, previously other places.
Omri Avrahami @OmriAvr
1K Followers 375 Following Researcher at @runwayml (Previously: @Snap, @NVIDIA, @GoogleAI, @MetaAI, @Lightricks). CS PhD from @HebrewU. Interested in #GenerativeAI.
ML Developer Programs @ml_ecosystem
35 Followers 312 Following
Fabrício Carraro @fabriciocarraro
6K Followers 670 Following O viajante poliglota. Host of podcast IA Sob Controle 🤖 TEDx Speaker | AI Developer Advocate & Research Engineer at BSC | AI Specialist at Alura
Jon Finger @mrjonfinger
25K Followers 726 Following Creative Workflow Executive @LumaLabsAi @dreamlabla
Elad Richardson @EladRichardson
2K Followers 1K Following Teaching Pixels New Tricks | Research @runwayml
Robera Geleta @RoberaGeleta
4K Followers 866 Following Build bespoke UI. Prototypes with UIKit/SwiftUI. Design Engineering - iOS @LumaLabsAI Before - iOS Eng 23-15 @tinder
Rivers Have Wings @RiversHaveWings
30K Followers 228 Following AI/generative artist. Writes her own code. Absolute power is a door into dreaming.
Theo Panagiotopoulos @theopanag7
2K Followers 1K Following Product at @LumaLabsAI, previously Apple
Keegan McCallum @keeganmccallum3
111 Followers 72 Following Building inference infrastructure for the interactive era https://t.co/mplYRTIvai 🟢
Joachim Sällström @jockesallstrom
59 Followers 94 Following AI art finetuner of Double Exposure, Aether Ghost and Aether Cloud etc.
Caroline Ingeborn @caroingeborn
534 Followers 147 Following COO @lumalabsAI Previously @leapchats @southparkcommons, @creandum, @tocaboca
Karan Ganesan @karanganesan
9K Followers 4K Following • founding engineer at luma ai (@lumalabsai) • prev at flipkart camera, scapic • an eclectic person interested in technologies of the future
Angela Dong @isthisangela
137 Followers 139 Following
Odyssey @odysseyml
34K Followers 12 Following We’re an AI lab pioneering world models—AI to understand and simulate the world.
Edwin Catmull @edcatmull
18K Followers 19 Following
Dumitru Erhan @doomie
19K Followers 2K Following Co-lead of Gemini Omni @GoogleDeepMind. Senior Research Director.
Jon Barron @jon_barron
34K Followers 1K Following Principal research scientist at Google DeepMind. Synthesized views are my own.
Omer Bar Tal @omerbartal
3K Followers 130 Following Founder @ Stealth, previously @runwayml @pika_labs @Google @WeizmannScience
Kody Kurth @kodykurth
2K Followers 549 Following Creative Director. AI Technologist. Viral Creator. Audiovisual Designer. VFX Supervisor. Experience Maker. Researcher & Developer. Cinematic Artist.
Colby Hawker @ColbyHawker
3K Followers 2K Following Generative AI Product Leader @Google. I lead - Agent Studio (Gemini EAP), & - Natural Language AI Sharing my 2cents on AI and technology trends.
will depue @willdepue
66K Followers 2K Following dei ex machina ex-@openai (sora 1 & 2, posttraining o3/4o, pretraining moonshots)
World Labs @theworldlabs
71K Followers 49 Following World Labs is a spatial intelligence company, building frontier models that can perceive, generate, and interact with the 3D world.
John Hewitt @johnhewtt
7K Followers 57 Following Assistant Prof @columbia CS. Visiting Researcher @ Google DeepMind. PhD from @stanfordnlp. Language x Neural Nets.























