kernels-community/flash-attn
Updated
•
5
kernels-community
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
drbh
updated
a
model
1 day ago
danieldk
updated
a
model
6 days ago
drbh
published
a
model
7 days ago
drbh
updated
a
model
9 days ago
Post
1402
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: 🤯
drbh
updated
3
models
22 days ago
Post
1613
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
danieldk
updated
a
model
23 days ago
danieldk
updated
a
model
about 1 month ago
danieldk
published
a
model
about 1 month ago
Post
7178
SmolVLM-2 and SigLIP-2 are now part of
They're added on top of the v4.49.0 release, and can be installed from the following tags:
This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures).
Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models.
Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.
transformers in dedicated releases!They're added on top of the v4.49.0 release, and can be installed from the following tags:
v4.49.0-SmolVLM-2 and v4.49.0-SigLIP-2.This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures).
Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models.
Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.
- 1 reply
Post
1710
Performance leap: TGI v3 is out. Processes 3x more tokens, 13x faster than vLLM on long prompts. Zero config !
3x more tokens.
By reducing our memory footprint, we’re able to ingest many more tokens and more dynamically than before. A single L4 (24GB) can handle 30k tokens on llama 3.1-8B, while vLLM gets barely 10k. A lot of work went into reducing the footprint of the runtime and its effect are best seen on smaller constrained environments.
13x faster
On long prompts (200k+ tokens) conversation replies take 27.5s in vLLM, while it takes only 2s in TGI. How so ? We keep the initial conversation around, so when a new reply comes in, we can answer almost instantly. The overhead of the lookup is ~5us. Thanks @Dani ël de Kok for the beast data structure.
Zero config
That’s it. Remove all the flags your are using and you’re likely to get the best performance. By evaluating the hardware and model, TGI carefully selects automatic values to give best performance. In production, we don’t have any flags anymore in our deployments. We kept all existing flags around, they may come in handy in niche scenarios.
Read more: https://huggingface.co/docs/text-generation-inference/conceptual/chunking
3x more tokens.
By reducing our memory footprint, we’re able to ingest many more tokens and more dynamically than before. A single L4 (24GB) can handle 30k tokens on llama 3.1-8B, while vLLM gets barely 10k. A lot of work went into reducing the footprint of the runtime and its effect are best seen on smaller constrained environments.
13x faster
On long prompts (200k+ tokens) conversation replies take 27.5s in vLLM, while it takes only 2s in TGI. How so ? We keep the initial conversation around, so when a new reply comes in, we can answer almost instantly. The overhead of the lookup is ~5us. Thanks @Dani ël de Kok for the beast data structure.
Zero config
That’s it. Remove all the flags your are using and you’re likely to get the best performance. By evaluating the hardware and model, TGI carefully selects automatic values to give best performance. In production, we don’t have any flags anymore in our deployments. We kept all existing flags around, they may come in handy in niche scenarios.
Read more: https://huggingface.co/docs/text-generation-inference/conceptual/chunking
Post
4474
Native tensor parallel has landed in transformers!!! https://github.com/huggingface/transformers/pull/34184 thanks a lot to the torch team for their support!
Contributions are welcome to support more models! 🔥
Contributions are welcome to support more models! 🔥
danieldk
authored
a
paper
9 months ago
Post
1993
text-generation-inference v2.0.3 is out.
Main new features:
- Falcon2 support
- PaliGemma support
- New faster speculation method from IBM !
https://github.com/huggingface/text-generation-inference/releases
Main new features:
- Falcon2 support
- PaliGemma support
- New faster speculation method from IBM !
https://github.com/huggingface/text-generation-inference/releases
Post
1302
text-generation-inference 2.0.2 is out.
- Native support for Idefics2, with much better efficiency than llava 1.6 (next) !
Phi3, Increase VLM support in the openai layer.
Release notes https://github.com/huggingface/text-generation-inference/releases/tag/v2.0.2
- Native support for Idefics2, with much better efficiency than llava 1.6 (next) !
Phi3, Increase VLM support in the openai layer.
Release notes https://github.com/huggingface/text-generation-inference/releases/tag/v2.0.2
ArthurZ
authored
a
paper
about 1 year ago
Post
mamba is now available in transformers. Thanks to
@tridao
and
@albertgu
for this brilliant model! 🚀 and the amazing mamba-ssm kernels powering this!Checkout the collection here:
state-spaces/transformers-compatible-mamba-65e7b40ab87e5297e45ae406
-
- 5 replies