22 | MLE @HuggingFace | Founder @tensoic | maintainer @ SGLang(@lmsysorg) | Prev: @iiscbangalore
🇮🇳
- Tweets 2,001
- Following 2,539
- Followers 1,964
- Likes 54,690
truly local models.
Our picks from this week's model releases 🦙
→ LFM3 by Liquid AI: small models for text, image and speech, with d1 decision models
→ Mistral Large 4: large, 1M context frontier
→ Flint by Recursive: mid-sized, built for coding agents
Get them at llama.app/models
1
8
378
🥁 I'll be speaking at the SGLang Summit, 2026!
SGLang (@sgl_project) is one of the most critical pieces of infrastructure in AI. Proud to represent Hugging Face at the Summit!
12
2
126
2,665
Adarsh retweeted
Congrats to @Baidu_Inc on Unlimited OCR 2! An entire book parsed in a single request, with decode latency and memory staying flat across hundreds of pages 👀
Proud to be the recommended serving path. Serving instructions are in the model card: huggingface.co/baidu/Unlimit…
Cookbook coming
Unlimited OCR 2 is here, and it's open source. 📖 ✨
Longer documents can mean a lot more attention computation. Our new SR-SWA mechanism keeps that in check by condensing text-visual attention interactions into a fixed-size set of working references.
Here's what it delivers:
- Document parsing at virtually any length, within a finite context window
- Nearly constant per-step decoding latency and memory footprint as documents grow longer
- State-of-the-art performance on MPDocBench and MarathonDocBench, covering documents from dozens to hundreds of pages
Check out the model here ↓
3
3
37
2,555
No that's exactly what a model regurgitating it's training env smoke test would do.
The prompt isn't asking the LLM to curl, it's asking the LLM to find a way to monitor if other things curl stuff. So if the LLM then starts with a test probe file and sends to a server that was never mentioned in the prompt or reasoning trace that is behaviour that's out of the ordinary. Again, not asserting malicious intent, we're flagging that it went out of bounds of the prompt in a potentially harmful way.
2
13
1,037
Adarsh retweeted
DeepInfer set the bar. SGLang pushed it higher! 🚀
SGLang now matches DeepInfer performance on BOTH prefill and decode:
• Prefill: Up to 1.04× throughput on 4× GB300 and 4× B300
• Decode: Up to 7.4% throughput on 64× GB300
We also provide an end-to-end reproduction guide and a full serving stack to run it in production.
35
79
667
192,833
I'll be at the SGLang Summit in SF! Looking forward to it
Whatever AI infra means to you, we’ve got it covered.
See for yourself: the SGLang Summit agenda is live → sglang.io/summit
🗓️ Nov 12–13 · 📍 Fort Mason, SF
🎟️ Early bird ends Oct 20
Two days of open models, AI hardware, recursive self-improvement, agents, robotics, and the systems behind them.
Featuring @LipBuTan1 (Intel), @lilianweng (OpenAI), @soumithchintala (Thinking Machines), @AravSrinivas (Perplexity) and researchers and builders from across the AI ecosystem.
Plus hands-on workshops on model training and serving decision models, hardware Expo, and plenty of community events.
What does AI infra mean to you?
3
34
4,248
Adarsh retweeted
A Durga Pujo gift from @bfl_ai and @diffuserslib to you folks!
FLUX 3 Klein is here. It is small, open, and really good.
huggingface.co/blog/flux-3
4
3
33
932
Adarsh retweeted
It's time. It's fucking time!
Flux.3 Image Klein is out and we bring you full support for it in Diffusers.
Catch all the details in our post:
huggingface.co/blog/flux-3
8
12
89
10,383
Adarsh retweeted
ok so we’re growing faster than I can keep up. I’m now the bottleneck.
Hiring semi-technical generalists for growth and founder’s office roles. Full-time and interns. Start ASAP.
SF preferred. Remote works if you learn fast.
DMs open. tell me the craziest hack you’ve pulled off.
87
15
500
42,785
Adarsh retweeted
3D worlds have been all over the internet 🌐 lately, so we put together the best ones across many models, for you to play with 🤗
introducing a new entry to the 3D-arena 🏟️ family, which focuses on LLM 3D Worlds 🌎
go and make your voice heard here 🚀:
huggingface.co/spaces/3d-are…
5
12
40
11,777
Adarsh retweeted
We have seen the OHCHR’s remarks about today’s events in New Delhi.
India is the world’s largest democracy, where the right to peaceful assembly is guaranteed by our Constitution and safeguarded by robust institutions, an independent judiciary and a free media. As in every democracy, Indian citizens exercise this right subject to reasonable restrictions in the interest of public order. The authorities, for their part, act in accordance with the law, and our courts remain available to all for redressal of any grievances.
The OHCHR’s concerns are therefore misplaced and constitute an unwarranted interference in the internal affairs of India.
In this context, OHCHR would also do well to devote comparable attention to large-scale protests elsewhere, consistent with its mandate of impartiality and non-selectivity.
@MEAIndia @IndianDiplomacy @PMOIndia @DrSJaishankar @abagchimea
3,240
8,388
30,533
1,129,694
Adarsh retweeted
Microduck got its new brain!
Our first fully custom SBC in a Pollen robot! It replaces the Radxa + board sandwich from the prototype.
Built by Seeed around the same Rockchip CPU but including better memory, better WiFi/BT, dual NFC antennas, user-facing status LEDs, an RGB flashlight, and major improvements in cooling, cable management and boot speed.
First revision arrived, and we got everything running on it within a day. Pretty good day :)
A big milestone on the road to shipping!
31
50
413
76,632
Adarsh retweeted
Announcing the first SGLang Summit: November 12–13 at Fort Mason, San Francisco.
Join us for two days of talks, discussions, and deep dives into frontier AI infrastructure, silicon, models, and applications.
Register: sglang.io/summit
15
47
210
1,774,659
RT @jsensarma: There should be no place for Departments like this in a STEM institute. It is not a scientific stream. It's built on Dogma a…
2
8
RT @jsensarma: Why STEM should stay away from Humanities wallas. Here's an example.
Consider this question: "Are more intelligent groups m…
21
7
Adarsh retweeted
Our Passport is absolutely useless.
Can’t go anywhere good without waiting for days for the Visa or submitting a thousand pages.
No wonder so many Indians are chasing other passports.
A valid US visa is the shortcut many use. Why do we need a US stamp to let an Indian Passport let in anywhere.
I pay almost 75L - 1 Cr in taxes directly and Indirectly a year and have zero advantages both locally or internationally.
We need to start fixing our country’s situation and stop blaming the past for few more decades.
#IndianPassport
405
224
2,142
214,129
Adarsh retweeted
Tokenizers v1's first release candidate is out 🔥 absolutely huge release across the board:
Up to 30x faster tokenization, rivaling the best in the ecosystem. Scaling across threads, much better latency, less memory consumed, and microscopic crate size.
huggingface.co/blog/tokenize…
14
20
167
21,085
Adarsh retweeted
tokenizers v1 (Rust): 3 to 30 times faster, opt-out tokenization training crate, lots of clever algorithms and optimizations, extensive benchmarks.
Coming soon to transformers.
huggingface.co/blog/tokenize…
4
8
94
10,116
Adarsh retweeted
Happy to officially bring you the new SOTA `tokenization` library.
We focused on all languages, multi-thread scaling, minimal package size and memory usage.
huggingface-tokenizers-v1.st…
We're thankful for the players of this ecosystem that have pushed us to give the best we could!
6
39
296
21,250
