Hugging Face's logo

Hugging Face Party @ PyTorch Conference
community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

mbrack  authored a paper about 2 months ago
UniFusion: Vision-Language Model as Unified Encoder in Image Generation
osanseviero  authored a paper 3 months ago
EmbeddingGemma: Powerful and Lightweight Text Representations
xiyang99  authored a paper 3 months ago
CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning
View all activity

csabakecskemeti 
posted an update 5 days ago
csabakecskemeti 
posted an update 6 days ago
view post
Post
2024
Looking for some help to test an INT8 Deepseek 3.2:
SGLang supports Channel wise INT8 quants on CPUs with AMX instructions (Xeon 5 and above AFAIK)
https://lmsys.org/blog/2025-07-14-intel-xeon-optimization/

Currently uploading an INT8 version of Deepseek 3.2 Speciale:
DevQuasar/deepseek-ai.DeepSeek-V3.2-Speciale-Channel-INT8

I cannot test this I'm on AMD
"AssertionError: W8A8Int8LinearMethod on CPU requires that CPU has AMX support"
(I assumed it can fall back to some non optimized kernel but seems not)

If anyone with the required resources (Intel Xeon 5/6 + ~768-1TB ram) can help to test this that would be awesome.

If you have hints how to make this work on AMD Threadripper 7000 Pro series please guide me.

Thanks all!
·
csabakecskemeti 
posted an update 29 days ago
view post
Post
302
Recently there are so much activity on token efficient formats, I've also build a package (inspired by toon).

Deep-TOON

My goal was to token efficiently handle json structures with complex embeddings.

So this is what I've built on the weekend. Feel free try:

https://pypi.org/project/deep-toon/0.1.0/
JingzeShi 
posted an update 29 days ago
csabakecskemeti 
posted an update about 2 months ago
view post
Post
2605
Christmas came early this year
·
osanseviero 
authored a paper 3 months ago
xiyang99 
authored 13 papers 3 months ago
lysandre 
posted an update 3 months ago
view post
Post
7100
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
·