Modular

1.2K posts

Modular banner
Modular

Modular

@Modular

Building AI’s unified compute layer. We are hiring → https://t.co/cPTAes0HMt 🚀

Beigetreten Ocak 2022
2 Folgt22.5K Follower
Angehefteter Tweet
Modular
Modular@Modular·
Gemma 4 is live on Modular Cloud, day zero, with the fastest performance on both NVIDIA and AMD. Our MAX inference framework delivers 15% higher throughput vs. vLLM on B200, and we’re the only inference provider to ship @googlegemma 4 on a framework we built ourselves. Two multimodal models live now: Gemma 4 31B (dense, 256K context) and 26B A4B (MoE, only 4B params active per pass). Both SOTA on Modular Cloud: modular.com/blog/day-zero-… Modular Cloud runs on MAX, our inference framework that unifies GPU kernels, graph compilation, and high-performance serving in a single hardware-agnostic stack. New weights to SOTA deployment in days, on two hardware platforms: modular.com/request-demo?u…
GIF
English
0
8
59
7.2K
Modular
Modular@Modular·
Highlights from @AMD AI DevDay 📷 Great to see so many developers at the booth and our reception the night before, and even better to watch their reactions when they saw MAX and Mojo 🔥 in action.
Modular tweet mediaModular tweet mediaModular tweet mediaModular tweet media
English
1
4
24
4.2K
Modular
Modular@Modular·
We're on the floor at @AMD AI DevDay! Stop by our booth to talk high-performance inference with AMD + Modular, and don't miss @clattner_llvm's luminary talk at 3:10 PM.
Modular tweet media
English
0
3
25
952
Modular
Modular@Modular·
Tonight in Jackson Square, we're hosting a small reception with AMD for founders, CTOs, and engineers running image and video gen in production. Registration is full, but join the waitlist and we'll let you know if a spot opens up: luma.com/full-context
English
0
0
3
794
Modular
Modular@Modular·
Tomorrow, @clattner_llvm takes the stage at @AMD's AI DevDay. He's covering FLUX.2 on the MI355X with Modular: 3.8x faster than torch.compile, 1024x1024 images in under 3.5 seconds, deployment container under 700MB. Register for DevDay: amd.com/en/corporate/e…
English
1
3
15
1.1K
Modular
Modular@Modular·
Ling-2.6-flash from @AntLingAGI is now open source, with day zero support on Modular Cloud! Fast MoE for agent workflows, without the deployment headache. Grab time with our team for a demo: modular.com/request-demo
Ant Ling@AntLingAGI

Ling-2.6-flash is now officially open-sourced! A fast, token-efficient Instruct model built for real-world agent workflows. 104B total parameters · 7.4B active parameters Available in BF16, FP8, and INT4 variants for different deployment needs. Key strengths: - Fast generation: 215 tokens/s on Artificial Analysis Output Speed - High token efficiency: only 15M tokens on the full AA Intelligence Index evaluation - Real task execution: strong performance across coding, document processing, and lightweight agent workflows - Improved experience: better Chinese-English switching and smoother compatibility with mainstream coding frameworks

English
0
4
26
4.7K
Modular
Modular@Modular·
Two days left until @AMD's AI DevDay! Don't miss @clattner_llvm's luminary talk covering how we fused FLUX.2 into a single execution graph, with a 3.8x speedup torch.compile on MI355X, under 3.5s per image, sub-700MB container. Plus, 5.5x lower cost than running on competing hardware. Stop by the Modular booth to connect with our team, learn about open roles, and score swag. Grab your spot: amd.com/en/corporate/e…
Modular tweet media
English
1
1
18
807
Modular
Modular@Modular·
@jog_soham Awesome talk! Thank you ❤️‍🔥
English
0
0
4
332
Modular
Modular@Modular·
Missed today's community meeting? The recording is now on our YouTube channel: youtube.com/watch?v=0gOGXH… Tune in to hear about Mojo support on Tensara and ffmpeg Mojo bindings. Built by the community, presented by the builders. Plus, catch Q&A at the end with the team.
YouTube video
YouTube
English
1
2
16
2.2K
Modular
Modular@Modular·
Uyo, Nigeria. May 2nd. If you're building with Mojo and MAX, this is your chance to connect with the community IRL. Live demos, roadmap updates, and a room full of developers who get it. Register: luma.com/mojo-africa
English
0
0
5
699
Modular
Modular@Modular·
April's community meeting is happening tomorrow, and we're spotlighting three impressive projects: - Marrow, an Apache Arrow implementation in Mojo by @kszucs_ - Mojo support on @tensarahq - MAV ffmpeg Mojo bindings Join us via Zoom: forum.modular.com/t/april-commun…
English
0
1
26
3.6K
Modular
Modular@Modular·
Ramine Roane @roaner, CVP of AI at @AMD, is joining the speaker lineup at Full Context. The night before AMD AI DevDay, we're gathering leaders in AI to talk all things image and video gen and high-performance inference. Light bites and drinks + raffle for a @AMDRadeon graphics card 👀 Grab your spot: luma.com/full-context
English
1
2
14
1.1K
Modular
Modular@Modular·
Modular's first Seoul developer meetup is coming up, co-hosted with SqueezeBits! 🇰🇷 Mark your calendars: May 19th at Belgium Jazz Cafe near COEX. The agenda includes Mojo, MAX, a session from the SqueezeBits team, a special message from @clattner_llvm, and a GPU raffle. Save your spot: luma.com/modular-seoul
English
1
5
16
3.9K
Modular
Modular@Modular·
The next day, @clattner_llvm presents the full breakdown: FLUX.2 as a single fused execution graph instead of four separate stages, compiled end-to-end with MLIR. On AMD MI355X, that's a 3.8x speedup over torch.compile, 1024x1024 images in under 3.5 seconds, and a deployment container under 700MB. 💪 Register for AMD AI DevDay: amd.com/en/corporate/e…
English
0
2
14
1.1K
Modular
Modular@Modular·
The night before @AMD AI DevDay, we're hosting a reception in Jackson Square with AMD for a small group of founders, CTOs, and engineers working on image and video gen in production. If you run inference at scale and want to talk shop, apply here: luma.com/full-context
English
1
2
17
1.4K
Modular retweetet
Ant Ling
Ant Ling@AntLingAGI·
Introducing Ling-2.6-flash, an instruct model with 104B total parameters and 7.4B active parameters. Ling-2.6-flash is designed for high token efficiency, not inflated outputs. It stays competitive on real agent tasks while helping developers reduce cost, improve throughput, and deploy more efficiently at scale.
English
23
60
702
4.3M
Modular
Modular@Modular·
.@AntLingAGI's Ling-flash-2.6 is live on Modular Cloud on day zero. The elephant-alpha model that trended on OpenRouter for days? This is it. 👀 104B parameters, 7.4B active. 256K context window. Built for speed and execution: code completion, document processing, lightweight agents. Fast inference on high-frequency, short-chain tasks. Runs well with OpenClaw and Hermes Agent. Solid as a coding execution subagent too. Book a demo to get started: modular.com/request-demo
English
0
5
30
9K
Modular
Modular@Modular·
The Modular community has been cooking! 🍳 During next week's community meeting, we'll hear about three community projects: - Marrow, an Apache Arrow implementation in Mojo - Mojo support on Tensara, a GPU programming challenge platform - MAV ffmpeg bindings for Mojo Join via Zoom: forum.modular.com/t/april-commun…
English
0
1
19
1.3K
Modular
Modular@Modular·
HDF5 is the file format behind most large scientific datasets: particle physics simulations, climate models, ML training pipelines. Now there are native bindings for Mojo. Load data straight into a NuMojo NDArray and run CPU/GPU processing in one pipeline, no format conversion. Check out the full post: forum.modular.com/t/hdf5-binding…
English
0
5
62
4.7K

Entdecken

@AMD @clattner_llvm @AntLingAGI @jog_soham @kszucs_ @tensarahq @AIatAMD @roaner