Dan Fu
@realDanFu
Followers
7K
Following
1K
Media
190
Statuses
813
VP, Kernels @togethercompute Assistant Professor @ucsd_cse Looking for talented kernel engineers and performance engineers!
Joined September 2019
Excited to share that I will be joining UCSD CSE as an assistant professor in January 2026! I'll be recruiting PhD students from the 2024 application pool - if you're interested in anything ML Sys/efficiency/etc please reach out & put my name on your application! Until then
47
40
573
It's pretty exciting to see this model on the platform - open-source models starting to match / outperform the SoTA frontier models!
🚀We're going live with @Kimi_Moonshot on Nov 19 for a technical deep dive on Kimi K2 Thinking Learn about the 1T parameter MoE that allows your AI agent to make 300 tool calls in one run. Register: https://t.co/JV3eIGqBtZ
1
0
6
🚀We're going live with @Kimi_Moonshot on Nov 19 for a technical deep dive on Kimi K2 Thinking Learn about the 1T parameter MoE that allows your AI agent to make 300 tool calls in one run. Register: https://t.co/JV3eIGqBtZ
2
3
16
🎬 Video generation is now available on Together AI Through our partnership with @Runware, we're integrating 20+ video models (Sora 2, Veo 3, PixVerse V5, Seedance) and 15+ image models All through the same APIs you use for text inference →
4
5
24
Great work on self-adaptive speculators led by @ben_athi and team! Very exciting!
Most speculative decoding research focuses on algorithms. But we know that data matters a ton! (e.g. no matter how good the spec algorithm is, if it's trained on bad & misaligned data, the speed will be poor) What if we build on algorithms that make data really shine?! In
0
0
7
Most speculative decoding research focuses on algorithms. But we know that data matters a ton! (e.g. no matter how good the spec algorithm is, if it's trained on bad & misaligned data, the speed will be poor) What if we build on algorithms that make data really shine?! In
together.ai
LLM inference that gets faster as you use it. Our runtime-learning accelerator adapts continuously to your workload, delivering 500 TPS on DeepSeek-V3.1, a 4x speedup over baseline performance...
This work, led by @_junxiong_wang and @ben_athi, is a first step towards building AI systems that evolve and get better as you use them. More to come!
0
5
25
Congrats @MichaelPoli6 @Massastrello @athmsx @exnx on the release! Building really cool things over at @RadicalNumerics :)
Introducing RND1, the most powerful base diffusion language model (DLM) to date. RND1 (Radical Numerics Diffusion) is an experimental DLM with 30B params (3B active) with a sparse MoE architecture. We are making it open source, releasing weights, training details, and code to
1
0
10
Cartridges from @EyubogluSabri is one of the more creative new approaches to modeling I’ve seen in a while - great work and great profile from @StanfordHAI!
@StanfordHAI just ran this story on self-study and cartridges -- it's a really nice overview for those curious about our work
0
2
10
@StanfordHAI just ran this story on self-study and cartridges -- it's a really nice overview for those curious about our work
1
19
45
Grafting is accepted to #NeurIPS2025 as an Oral! New methods for converting a trained diffusion transformer into a new architecture (like Hyena, SSM, etc). Really top-notch work by @keshigeyan on this one. Check out his post below for demos, analysis, and models!
Grafting Diffusion Transformers accepted to #NeurIPS2025 as an Oral! We have lots of interesting analysis, a test bed for model grafting, and insights🚀 📄Paper: https://t.co/OjsrOZi7in 🌎Website:
0
2
18
Grafting Diffusion Transformers accepted to #NeurIPS2025 as an Oral! We have lots of interesting analysis, a test bed for model grafting, and insights🚀 📄Paper: https://t.co/OjsrOZi7in 🌎Website:
arxiv.org
Designing model architectures requires decisions such as selecting operators (e.g., attention, convolution) and configurations (e.g., depth, width). However, evaluating the impact of these...
1/ Model architectures have been mostly treated as fixed post-training. 🌱 Introducing Grafting: A new way to edit pretrained diffusion transformers, allowing us to customize architectural designs on a small compute budget. 🌎 https://t.co/fjOTVqfVZr Co-led with @MichaelPoli6
7
36
206
It's really exciting to see @OpenAI releasing open-source models again. These models look really great, excited to see what we can do with them! 120B available now on @togethercompute, more coming soon!
🤖OpenAI's open models are here. gpt-oss models just landed on Together AI. Achieves near-parity with o4- mini, trained using o3 techniques. Build anything, deploy anywhere🔥
0
0
15
🤖OpenAI's open models are here. gpt-oss models just landed on Together AI. Achieves near-parity with o4- mini, trained using o3 techniques. Build anything, deploy anywhere🔥
13
24
112
Crazy fast!! Great work from @haoailab
(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live
0
1
4
DeepCogito models available and scaling on Together, check them out
A small update - we had more traffic than anticipated. However, the endpoints are now scalable on Together AI for all models, including the 671B MoE. Test out the model here: https://t.co/Od1NXYVBxU (A huge thanks to the folks at @togethercompute for making this happen so
0
0
3
It’s been great working with you @mjlbach! Great models + great kernels & infra -> amazing things
Working with @togethercompute has been one of the greatest accelerants for our research & inference team. We've scaled to thousands of chips seamlessly and migrated across multiple architectures thanks to their amazing kernel group. @vipulved is also a personal icon of mine.
0
0
2
I really enjoyed this talk from @bariskasikci at @ESFoMo - some really fine-grained analysis of compute patterns of LLM serving in the throughput-bound regime, and how to schedule operations to push the boundaries (a linear program)! Great work!
0
3
15
ES-FoMo is back tomorrow! Come join is in East Exhibition Hall A bright and early at 8:30AM for a great slate of invited talks, orals, spotlight lightning talks, and 150 posters!
Looking forward to seeing everyone for ES-FoMo part three tomorrow! We'll be in East Exhibition Hall A (the big one), and we've got an exciting schedule of invited talks, orals, and posters planned for you tomorrow. Let's meet some of our great speakers! 1/
0
3
14
Looking forward to seeing everyone for ES-FoMo part three tomorrow! We'll be in East Exhibition Hall A (the big one), and we've got an exciting schedule of invited talks, orals, and posters planned for you tomorrow. Let's meet some of our great speakers! 1/
3
23
80
And @keshigeyan is going to be presenting about Grafting - a great collaboration with @MichaelPoli6 on how to distill pretrained diffusion models into new architectures (Transformers -> Hyenas) 4/
1/ Model architectures have been mostly treated as fixed post-training. 🌱 Introducing Grafting: A new way to edit pretrained diffusion transformers, allowing us to customize architectural designs on a small compute budget. 🌎 https://t.co/fjOTVqfVZr Co-led with @MichaelPoli6
0
3
7
Two papers at the workshop I’m a bit fond of… @austinsilveria and @SohamGovande are going to be presenting Chipmunk - come chat with them about how they made video diffusion 3.7x faster! (With custom column-sparse attention kernels) 3/
Training-free acceleration of Diffusion Transformers with dynamic sparsity and cross-step attention/MLP deltas--collaboration with @SohamGovande and @realDanFu! ⚡️ 3.7x faster video and 1.6x faster image generation while preserving quality! 🧵 Open-source code & CUDA kernels!
1
2
10