appughar (@appughar) header
appughar (@appughar) profile picture

CEO & co-founder, Mobius Labs (exited to Dropbox). Making Dash multimodal. Trying to make computers see.

space-time continuum
Joined December 2008
Photo by appughar (@appughar)Photo by appughar (@appughar)Photo by appughar (@appughar)Photo by appughar (@appughar)Photo by appughar (@appughar)Photo by appughar (@appughar)Photo by appughar (@appughar)Photo by appughar (@appughar)Photo by appughar (@appughar)Photo by appughar (@appughar)
If you’re at @EurIPSConf this week and looking for your next ML role, ping us. Few of us from @Dropbox including @mobicham @appughar will be there Happy to chat about roles in multimodal, search, and video-AI.
Replying to @Mobius_Labs
Looking for people with experience in : Building and scaling multimodal ML systems, Retrieval, ranking, and creative search problems, Turning prototypes into polished products 🌍 Remote (Germany or Denmark) Apply here: jobs.dropbox.com/listing/738… (Please use the link, not DMs!)
2
4
661
appughar retweeted
Well optimized Triton kernels can perform very well end-2-end, even competing with highly optimized kernels like Marlin.
2
4
40
5,732
Our re-distilled @deepseek_ai R1 (1.5B) outperforms the original distilled model! Get it at huggingface.co/mobiuslabsgmb…. We’re distilling more models and look forward to releasing them soon!
10
61
14
401
34,797
i'm comically impressed that people are coping on deepseek by spewing bizarre conspiracy theories -- despite deepseek open-sourcing and writing some of the most detail oriented papers ever. read. replicate. compete. don't be salty, just makes you look incompetent.
95
385
37
4,018
314,164
appughar retweeted
Heard you like distillation, so we re-distilled the distilled model
2
4
297
It was a real pleasure and a productive experience collaborating with the team at @PyTorch and the SGlang team at @lmsysorg to bring gemlite to TorchAO and SGLang. This is an exciting area that requires a lot of work. Let’s push the boundaries of efficient computing!
Scaling Large Language Models (#LLMs) is tough due to resource demands. Quantization helps but often comes with trade-offs in accuracy and performance. Discover how #PyTorch, Mobius Labs, and SGLang tackled these challenges with Gemlite, TorchAO, and SGLang for efficient low-precision inference. 📖 Read here: hubs.la/Q033z_kw0
1
6
16
2,878
Releasing a new version of Gemlite github.com/mobiusml/gemlite significantly improved performance on datacenter GPUS  (A100/H100) delivering up to 7–8x faster prefill and 3–6x faster decoding compared to PyTorch's tinygemm.
1
5
12
654
Check out our own @mobicham's lecture on building low-bit Triton kernels & the impressive speedups we’re achieving with them, presented at @GPU_MODE channel. Also includes plenty of tips & tricks for performance tuning in Triton & GPU programming. youtube.com/watch?v=7c3c3bCG…
6
1
13
1,760
Replying to @mobicham
@mobicham will be talking about low-bit Triton kernels and his experience building github.com/mobiusml/gemlite this Saturday at the GPU mode discord. It’s sure to be a great session if you’re interested in efficiency! discord.gg/KKkmtQPx?event=12…
5
1
12
4,978
I really like the newly unveiled statue of Satoshi Nakamoto in #Lugano. Especially the way it honors privacy. Depending on the perspective, it disappears. #PlanBForum #privacy 🇨🇭
287
1,914
247
14,636
1,068,939
appughar retweeted
pushing Truchet boxes with #threejs
92
819
50
6,153
210,833
At Mobius Labs, with our academic roots, we often debate publishing papers. But business pressures and the angst about the prodigal reviewer bent on pressing the reject button, have led us to focus on blogs and open-source work instead. Check some of it at blog.mobiuslabs.com
ICLR 2025 will have another blogpost track! If you have new intuitions on past work, noticed key implementation details for reproducibility, have insights into the societal implications of AI, or an interesting negative result, consider writing and submitting a blogpost. Accepted entries will have the opportunity to be presented as a poster at ICLR2025 (in Singapore)! Deadline: Before Nov. 16 2024 More info: iclr-blogposts.github.io/202…
3
5
461
We’re thrilled to announce that our team at Mobius Labs has won Runner-Up in the SoccerNet Game State Reconstruction Challenge, in collaboration with @IRI_robotics 🏆⚽
1
5
8
557
This! One of the pleasures of open source is building together. You learn, iterate, & share ideas fast. Startups stuck in closed environments only reach local optima at best. Open source expands your perspective, connects you with great people, & delivers quality with quantity.
1
2
8
510
We benchmarked the new OpenAI's whisper-turbo model using long-form audio (5+ mins) with faster-whisper ( github.com/SYSTRAN/faster-wh…) backend. Results ( as-expected): It achieves WER comparable to large models and excels in speed among multilingual models.
1
2
6
698
CUDA MODE has grown up! -> GPU MODE
From the beginning, @neurosp1ke and I wanted a community that was cozy, inclusive and fun where you could make friends and learn how to make your code faster Anyone who shares our ideals is welcome. We’re announcing we’re changing the name of our community to “GPU MODE”.
3
47
4,236
appughar retweeted
CUDA MODE Hackathon was amazing! Had some time to hack some 3-bit and 5-bit Triton GEMM kernels 🚀
4
59
4,798