Thanks for the ping, @John6666
If that workaround solves this, then great! We'll keep digging into the root cause. Appreciate the additional example.
Jared Sulzdorf PRO
jsulz
AI & ML interests
Infrastructure, law, policy
Recent Activity
commented on
an
article
about 2 hours ago
Parquet Content-Defined Chunking
updated
a dataset
about 7 hours ago
jsulz/ready-xet-go
updated
a model
1 day ago
jsulz/random-upload-tests
Organizations
replied to
zeeshanirshad95's
post
5 days ago
reacted to
erikkaum's
post with 🤗
10 days ago
Post
1970
We just released native support for
@SGLang
and
@vllm-project
in Inference Endpoints 🔥
Inference Endpoints is becoming the central place where you deploy high performance Inference Engines.
And that provides the managed infra for it. Instead of spending weeks configuring infrastructure, managing servers, and debugging deployment issues, you can focus on what matters most: your AI model and your users 🙌
Inference Endpoints is becoming the central place where you deploy high performance Inference Engines.
And that provides the managed infra for it. Instead of spending weeks configuring infrastructure, managing servers, and debugging deployment issues, you can focus on what matters most: your AI model and your users 🙌
replied to
their
post
13 days ago
@nyuuzyou some high-level plans here if you're interested https://huggingface.co/blog/migrating-the-hub-to-xet
posted
an
update
13 days ago
Post
2796
We've moved over 20PB from Git LFS to Xet on the Hub without downtime or data loss. Having things "just work" on a migration of this scale is about as good as it gets.
Now, we're migrating the rest of the Hub https://huggingface.co/blog/migrating-the-hub-to-xet
But how did we get here?
In the early days of joining Hugging Face, we made a few key design decisions:
* There would be no "hard cut-over" from Git LFS to Xet
* A Xet-enabled repository should be able to contain both Xet and LFS files
* Repository migrations from LFS to Xet can run in the background without disrupting downloads or uploads
These were largely driven by our desire to ensure the community could keep working without interruption.
We cover the infrastructure making this all go in this post, specifically:
* An integral piece of infrastructure known internally as the Git LFS Bridge
* Background content migrations that run around the clock
To skip the wait and join Xet now, sign up here https://huggingface.co/join/xet
Now, we're migrating the rest of the Hub https://huggingface.co/blog/migrating-the-hub-to-xet
But how did we get here?
In the early days of joining Hugging Face, we made a few key design decisions:
* There would be no "hard cut-over" from Git LFS to Xet
* A Xet-enabled repository should be able to contain both Xet and LFS files
* Repository migrations from LFS to Xet can run in the background without disrupting downloads or uploads
These were largely driven by our desire to ensure the community could keep working without interruption.
We cover the infrastructure making this all go in this post, specifically:
* An integral piece of infrastructure known internally as the Git LFS Bridge
* Background content migrations that run around the clock
To skip the wait and join Xet now, sign up here https://huggingface.co/join/xet
reacted to
burtenshaw's
post with ❤️
26 days ago
Post
2812
Inference for generative ai models looks like a mine field, but there’s a simple protocol for picking the best inference:
🌍 95% of users >> If you’re using open (large) models and need fast online inference, then use Inference providers on auto mode, and let it choose the best provider for the model. https://huggingface.co/docs/inference-providers/index
👷 fine-tuners/ bespoke >> If you’ve got custom setups, use Inference Endpoints to define a configuration from AWS, Azure, GCP. https://endpoints.huggingface.co/
🦫 Locals >> If you’re trying to stretch everything you can out of a server or local machine, use Llama.cpp, Jan, LMStudio or vLLM. https://huggingface.co/settings/local-apps#local-apps
🪟 Browsers >> If you need open models running right here in the browser, use transformers.js. https://github.com/huggingface/transformers.js
Let me know what you’re using, and if you think it’s more complex than this.
🌍 95% of users >> If you’re using open (large) models and need fast online inference, then use Inference providers on auto mode, and let it choose the best provider for the model. https://huggingface.co/docs/inference-providers/index
👷 fine-tuners/ bespoke >> If you’ve got custom setups, use Inference Endpoints to define a configuration from AWS, Azure, GCP. https://endpoints.huggingface.co/
🦫 Locals >> If you’re trying to stretch everything you can out of a server or local machine, use Llama.cpp, Jan, LMStudio or vLLM. https://huggingface.co/settings/local-apps#local-apps
🪟 Browsers >> If you need open models running right here in the browser, use transformers.js. https://github.com/huggingface/transformers.js
Let me know what you’re using, and if you think it’s more complex than this.
replied to
their
post
about 1 month ago
@nyuuzyou we definitely want everyone to be on Xet in the future, so yup!
posted
an
update
about 1 month ago
Post
4597
It's been a bit since I took a step back and looked at
xet-team
progress to migrate Hugging Face from Git LFS to Xet, but every time I do it boggles the mind.
A month ago there were 5,500 users/orgs on Xet with 150K repos and 4PB. Today?
🤗 700,000 users/orgs
📈 350,000 repos
🚀 15PB
Meanwhile, our migrations have pushed throughput to numbers that are bonkers. In June, we hit upload speeds of 577Gb/s (crossing 500Gb/s for the first time).
These are hard numbers to put into context, but let's try:
The latest run of the Common Crawl from
commoncrawl
was 471 TB.
We now have ~32 crawls stored in Xet. At peak upload speed we could move the latest crawl into Xet in about two hours.
We're moving to a new phase in the process, so stay tuned.
This shift in gears means it's also time to roll up our sleeves and look at all the bytes we have and the value we're adding to the community.
I already have some homework from @RichardErkhov to look at the dedupe across their uploads, and I'll be doing the same for other early adopters, big models/datasets, and frequent uploaders (looking at you @bartowski 👀)
Let me know if there's anything you're interested in; happy to dig in!
xet-team
progress to migrate Hugging Face from Git LFS to Xet, but every time I do it boggles the mind.A month ago there were 5,500 users/orgs on Xet with 150K repos and 4PB. Today?
🤗 700,000 users/orgs
📈 350,000 repos
🚀 15PB
Meanwhile, our migrations have pushed throughput to numbers that are bonkers. In June, we hit upload speeds of 577Gb/s (crossing 500Gb/s for the first time).
These are hard numbers to put into context, but let's try:
The latest run of the Common Crawl from
commoncrawl
was 471 TB. We now have ~32 crawls stored in Xet. At peak upload speed we could move the latest crawl into Xet in about two hours.
We're moving to a new phase in the process, so stay tuned.
This shift in gears means it's also time to roll up our sleeves and look at all the bytes we have and the value we're adding to the community.
I already have some homework from @RichardErkhov to look at the dedupe across their uploads, and I'll be doing the same for other early adopters, big models/datasets, and frequent uploaders (looking at you @bartowski 👀)
Let me know if there's anything you're interested in; happy to dig in!
-
- 5 replies
reacted to
merve's
post with 🔥
about 1 month ago
Post
3712
stop writing CUDA kernels yourself
we have launched Kernel Hub: easy optimized kernels for all models on Hugging Face 🔥 use them right away!
it's where the community populates optimized kernels 🤝
this release comes in three parts
> Kernel Hub: contains (as of now) 14 kernels
> kernels: Python library to load kernels from Kernel Hub
> kernel-builder: Nix package to build kernels for PyTorch (made using PyTorch C++ frontend)
when building models, your regular workflow should be pulling kernels from Hub and building your model with them 🤗
here's a practical example with RMSNorm:
1. pull the kernel from Hub with
2. decorate with
3. inject it to your model
we'd love to hear your feedback! 🙏🏻
we also welcome kernel contributions by community 🥹💗
- request kernels here: kernels-community/README#1
- check out this org:
kernels-community
- read the blog: https://huggingface.co/blog/hello-hf-kernels
we have launched Kernel Hub: easy optimized kernels for all models on Hugging Face 🔥 use them right away!
it's where the community populates optimized kernels 🤝
this release comes in three parts
> Kernel Hub: contains (as of now) 14 kernels
> kernels: Python library to load kernels from Kernel Hub
> kernel-builder: Nix package to build kernels for PyTorch (made using PyTorch C++ frontend)
when building models, your regular workflow should be pulling kernels from Hub and building your model with them 🤗
here's a practical example with RMSNorm:
1. pull the kernel from Hub with
get_kernel2. decorate with
use_kernel_forward_from_hub3. inject it to your model
we'd love to hear your feedback! 🙏🏻
we also welcome kernel contributions by community 🥹💗
- request kernels here: kernels-community/README#1
- check out this org:
kernels-community
- read the blog: https://huggingface.co/blog/hello-hf-kernels
- 1 reply
reacted to
Narsil's
post with 🚀
about 2 months ago
Post
1759
Me: This function is too slow. Find a faster algorithm.
Cursor: Hold my beer.
Me: *Slacking off with colleagues*
Cursor: Ping.
Me: 🤯
Cursor: Hold my beer.
Me: *Slacking off with colleagues*
Cursor: Ping.
Me: 🤯
reacted to
danieldk's
post with 🤗🔥
about 2 months ago
Post
1734
We have been working on a project called
We plan to give kernels a more proper introduction soon. But for those who have been following along, we are happy to announce a new release:
- New layer API with
- Experimental support for loading Apple Silicon Metal 🤘 Kernels.
- Generate wheels from Hub kernels for legacy deployments.
Full release notes here: https://github.com/huggingface/kernels/releases/tag/v0.6.0
kernels. kernels makes it possible to load compute kernels directly from the Hub! 🚀We plan to give kernels a more proper introduction soon. But for those who have been following along, we are happy to announce a new release:
- New layer API with
torch.compile support.- Experimental support for loading Apple Silicon Metal 🤘 Kernels.
- Generate wheels from Hub kernels for legacy deployments.
Full release notes here: https://github.com/huggingface/kernels/releases/tag/v0.6.0
replied to
their
post
about 2 months ago
Hey @RichardErkhov we've begun onboarding you to Xet! 🚀
All new repos you create will be Xet-enabled by default and your existing repos are being migrated as we speak.
Since you have a lot of repos the migration of existing content may take some time. While it's ongoing you may notice instances where a repo is a mixture of LFS and Xet-backed files. This shouldn't be an problem due to how we manage backwards compatibility, but if you have any issues, please let me know here.
For new repos you create, just make sure to follow the instructions here to get the full benefits of using Xet storage.
I'll follow up here once all of your repos have been moved over!
Hey @mradermacher sorry for the delay; just wanted to let you know that your migration to Xet should be complete!
Feel free to ping me here if you have any questions or feedback. Excited to hear how it's been going! 🤗
Also, if you have any issues, don't hesitate to open a discussion here https://huggingface.co/spaces/xet-team/README/discussions or an issue on this repo https://github.com/huggingface/xet-core
posted
an
update
2 months ago
Post
742
With major model families like
Qwen
and all of Llama from
meta-llama
on Xet, the time is right for new users and organizations to say goodbye to LFS on the Hub.
Xet is now the default storage for new AI builders 🚀 🚀 🚀
Just sign up for an account, create a new model or dataset, pip install huggingface_hub and you're off to the races!
Read more here https://huggingface.co/changelog/xet-default-for-new-users
And for everyone with existing repositories, just sign up here https://huggingface.co/join/xet - we'll migrate all existing repositories to Xet and all new repos you create will be Xet-backed by default.
Qwen
and all of Llama from
meta-llama
on Xet, the time is right for new users and organizations to say goodbye to LFS on the Hub. Xet is now the default storage for new AI builders 🚀 🚀 🚀
Just sign up for an account, create a new model or dataset, pip install huggingface_hub and you're off to the races!
Read more here https://huggingface.co/changelog/xet-default-for-new-users
And for everyone with existing repositories, just sign up here https://huggingface.co/join/xet - we'll migrate all existing repositories to Xet and all new repos you create will be Xet-backed by default.
reacted to
merve's
post with 🤗🔥🚀
2 months ago
Post
3170
Bu post'u çevirebilirsiniz 🤗💗
- 6 replies
Hey @mradermacher just wanted to let you know that we've begun onboarding you to Xet!
All new repos that you create will be Xet-enabled by default. We are still migrating existing repos, so you will see times when there are a mixture of LFS and Xet files side-by-side, but as the migration progresses everything will become Xet.
As I mentioned in my last message, none of this is an issue due to how we've designed the system for backward compatibility, but if you have any questions or concerns, please let me know. Otherwise, I'll follow up here once all your repos are migrated!
reacted to
celinah's
post with 😎🤗
2 months ago
Post
2336
✨ Today we’re releasing Tiny Agents in Python — an MCP-powered Agent in ~70 lines of code 🐍
Inspired by Tiny Agents in JS from @julien-c , we ported the idea to Python and integrated it directly into
TL;DR: With MCP (Model Context Protocol), you can expose tools like web search or image generation and connect them directly to LLMs. It’s simple — and surprisingly powerful.
We wrote a blog post where we show how to run Tiny Agents, and dive deeper into how they work and how to build your own.
👉 https://huggingface.co/blog/python-tiny-agents
Inspired by Tiny Agents in JS from @julien-c , we ported the idea to Python and integrated it directly into
huggingface_hub — with a built-in MCP Client and a Tiny Agents CLI.TL;DR: With MCP (Model Context Protocol), you can expose tools like web search or image generation and connect them directly to LLMs. It’s simple — and surprisingly powerful.
pip install "huggingface_hub[mcp]>=0.32.0"We wrote a blog post where we show how to run Tiny Agents, and dive deeper into how they work and how to build your own.
👉 https://huggingface.co/blog/python-tiny-agents
- 1 reply