Hugging Face's logo

SLLHF
community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
eliebak  authored a paper about 2 months ago
Prime Agent: A Self-Improving RLM Harness
eliebak  authored a paper about 2 months ago
How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data
clefourrier  authored a paper 7 months ago
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
View all activity
danieldk 
posted an update 3 months ago
view post
Post
255
We have recently added Torch Stable ABI support to kernels and kernel-builder. This allows kernel developers to target a particular Torch version and the kernel will be supported on that Torch version and later Torch versions (up to ~2 years).

This makes it much easier to write kernels with long-term support and not just the last two Torch releases.

We have also started rolling out Stable ABI support to kernels in kernels-community, starting with Flash Attention 3, supporting Torch 2.9 and later as well as CUDA versions starting at 12.6:

https://huggingface.co/kernels/kernels-community/flash-attn3/tree/v1/build
  • 1 reply
·
victor 
posted an update 5 months ago
view post
Post
6256
Sharing how I built the LongCat-Video-Avatar 1.5 Space (+500k views on X) in one agent session. Gave a coding agent its own AI lab on ZeroGPU, framed the goal, walked away. It designed, deployed, tested against the live API, fixed, shipped.

Full recipe with the copy-paste prompt: https://huggingface.co/blog/victor/building-zerogpu-spaces-autonomously
  • 1 reply
·
alvarobartt 
posted an update 5 months ago
view post
Post
2186
Open agents on AWS SageMaker AI with open models from the Hugging Face Hub!

> Deploy an open model from the Hugging Face Hub on SageMaker AI
> Connect the deployed model to Strands Agents
> Add built-in and custom tools for tool calling
> Expose external capabilities through MCP integration
> Bonus: talk to your agent and visualize traces with Gradio

https://alvarobartt.com/agents-on-aws-sagemaker
danieldk 
posted an update 5 months ago
view post
Post
295
Two large changes in kernel-builder this week:

kernel-builder now links libstdc++ dynamically. To support a wide range of systems, we build against libstdc++ from manylinux_2_28 (EL 8 and later).

Following our Torch support policy that the current and previous Torch versions are supported, Torch 2.10 support was removed. We will soon also support the Torch stable ABI, so that it is possible to write kernels that support a large number of Torch versions.
alvarobartt 
posted an update 5 months ago
view post
Post
4689
Latest hf-mem release added a breakdown of Mixture-of-Experts (MoE) memory usage!

TL; DR MoEs can be misleading to reason about from active parameters alone, since each token only activates a subset of experts, while the serving setup still needs to account for the full resident memory footprint.

🧠 hf-mem now splits MoE memory into base model weights, routed experts, and KV cache
🏗️ Dense models usually load and use most weights every forward pass, while MoEs load many experts but only route each token to a few of them
⚡ Active params isn't the same as memory footprint, especially for sparse architectures
📦 Runtime memory is about what is used per request/token, while loading memory also includes the expert weights that need to be resident
📚 KV cache can still dominate depending on context length, batch size, and concurrency
🔀 Expert Parallelism (EP) helps shard experts across accelerators when expert weights dominate
🚀 Data Parallelism (DP) + EP is often a good fit for throughput-oriented MoE serving

Check the repository at https://github.com/alvarobartt/hf-mem
victor 
posted an update 6 months ago
view post
Post
6349
Want to share my enthusiasm for zai-org/GLM-5.1 here too 🔥

I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:

- One-shot car physics with real drift mechanics (this is hard)

- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen

- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters

- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!

- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed

You are going to hear about this model a lot in the next months - open source let's go - and thanks z-ai🚀🚀
  • 5 replies
·
clefourrier 
authored a paper 7 months ago
alvarobartt 
posted an update 7 months ago
view post
Post
4609
Learn how to deploy Microsoft Research VibeVoice ASR on Microsoft Azure Foundry with Hugging Face to generate rich audio transcriptions with Who, When, and What! 💥

> 🕒 60-minute single-pass processing, no chunking or stitching
> 👤 Customized hotwords to guide recognition on domain-specific content
> 📝 Rich transcription: joint ASR + diarization + timestamping in one pass
> 🌍 50+ languages with automatic detection and code-switching support
> 🤗 Deployed on Microsoft Foundry via an OpenAI-compatible Chat Completions API

https://huggingface.co/docs/microsoft-azure/foundry/examples/deploy-vibevoice-asr
victor 
submitted a paper to Daily Papers 8 months ago
mryab 
submitted a paper to Daily Papers 8 months ago
victor 
posted an update 8 months ago
view post
Post
2909
Interesting article: use Claude Code to help open models write CUDA kernels (for eg) by turning CC traces into Skills. They made a library out of it 👀

https://huggingface.co/blog/upskill
alvarobartt 
posted an update 9 months ago
view post
Post
3847
💥 hf-mem v0.4.1 now also estimates KV cache memory requirements for any context length and batch size with the --experimental flag!

uvx hf-mem --model-id ... --experimental will automatically pull the required information from the Hugging Face Hub to include the KV cache estimation, when applicable.

💡 Alternatively, you can also set the --max-model-len, --batch-size and --kv-cache-dtype arguments (à la vLLM) manually if preferred.
  • 1 reply
·
danieldk 
posted an update 9 months ago
view post
Post
2848
kernels 0.12 is out! 🎉

Changes:

* Support for kernel version branches to gracefully roll out kernel API changes.
* Support for PyTorch 2.10.
* kernel-builder is now merged into the kernels repo.
* Initial support for standardized kernel benchmarks.

https://github.com/huggingface/kernels/releases/tag/v0.12.0
victor 
posted an update 10 months ago
danieldk 
posted an update 12 months ago
m-ric 
posted an update 12 months ago
view post
Post
2487
Tokenization is one of the most important processes in AI - yet many would like to kill it 💀

What's tokenization? The neural networks inside LLMs actually only process numbers, not text: tokenization is the process that makes text readable for them, by converting sentences into lists of numbers.

➡️ For instance, "This is tokenization" would be split into "This | is | token | ization", then each of the parts (tokens) are converted to IDs according to a predefined mapping: for instance "ization" could map to id 2438.
Thus "This is tokenization" can become 1335 | 135 | 2980 | 2438 => now the model can process the sentence!

Most tokenizers today use pre-specified mappings called "vocabularies", generally built about the compression algorithme Byte-Pair Encoding (BPE) that learns from a big corpuses of texts an optimized split to efficiently encode any text from the same distribution into a list token IDs.

🤨 Now, these current tokenizers have flaws.
For instance, the rigidity of their mapping creates losses ; the prime example being that a tokenizer designed for English (thus optimized for tokens like "has", "been", "clock", etc) will not have the right tokens to approach Burmese, thus being terribly inefficient at it.

Many alternative approaches have emerged as a result: for instance "tokenizer-free tokenizers". One that I really liked was "entropy-based": it monitors the stream of text, and trigger a split whenever the entropy increases too much, i.e. when something "surprising" happens.

But this great article argues that tokenizers are a lesser evil. Read and decide for yourself!
https://huggingface.co/blog/catherinearnett/in-defense-of-tokenizers
hfkwr 
authored a paper about 1 year ago
m-ric 
posted an update about 1 year ago
view post
Post
5143
STOP EVERYTHING NOW - we might finally have a radical architecture improvement over Transformers!!! 🚨

A lone scientist just proposed Tiny Recursive Model (TRM), and it is literally the most impressive model that I've seen this year.

➡️ Tiny Recursive Model is 7M parameters
➡️ On ARC-AGI, it beats flagship models like Gemini-2.5-pro

Consider how wild this is: Gemini-2.5-pro must be over 10,000x bigger
and had 1,000 as many authors 😂 (Alexia is alone on the paper)

What's this sorcery?
In short: it's a very tiny Transformers, but it loops over itself at two different frequencies, updating two latent variables: one for the proposed answer and one for the reasoning.

@AlexiaJM started from the paper Hierarchical Reasoning Model, published a few months ago, that already showed breakthrough improvement on AGI for its small size (27M)

Hierarchical Reasoning Model had introduced one main feature:
🔎 Deep supervision
In their model, one part (here one layer) would run at high frequency, and another would be lower frequency, running only every n steps.

They had used a recurrent architecture, where these layers would repeat many times ; but to make it work they had to do many approximations, including not fully backpropagating the loss through all layers.

Alexia studied what was useful and what wasn't, and cleaned the architecture as follows :
Why use a recurrent architecture, when you can just make it a loop?
➡️ She made the network recursive, looping over itself

Why use 2 latent variables ?
➡️ She provides a crystal clear explanation : the one that changes frequently is the reasoning, the one that changes at low frequency is the proposed answer.
➡️ She runs ablation studies to validate that 2 is indeed optimal.

This new setup is a much more elegant way to process reasoning than generating huge chains of tokens as all flagship models currently do.

This might be the breakthrough we've been awaiting for so long!
  • 4 replies
·
lysandre 
posted an update about 1 year ago
view post
Post
10321
We're kick-starting the process of Transformers v5, with @ArthurZ and @cyrilvallez !

v5 should be significant: we're using it as a milestone for performance optimizations, saner defaults, and a much cleaner code base worthy of 2025.

Fun fact: v4.0.0-rc-1 came out on Nov 19, 2020, nearly five years ago!
  • 6 replies
·
Wauplin 
posted an update about 1 year ago
view post
Post
3874
Say hello to hf: a faster, friendlier Hugging Face CLI ✨

We are glad to announce a long-awaited quality-of-life improvement: the Hugging Face CLI has been officially renamed from huggingface-cli to hf!

So... why this change?

Typing huggingface-cli constantly gets old fast. More importantly, the CLI’s command structure became messy as new features were added over time (upload, download, cache management, repo management, etc.). Renaming the CLI is a chance to reorganize commands into a clearer, more consistent format.

We decided not to reinvent the wheel and instead follow a well-known CLI pattern: hf <resource> <action>. Isn't hf auth login easier to type and remember?

The full rationale, implementation details, and migration notes are in the blog post: https://huggingface.co/blog/hf-cli

  • 7 replies
·