Marc Sun

marcsun13's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article 22 days ago

view article

Article

Transformers v5: Simple model definitions powering the AI ecosystem

• 
• 
• +2

25 days ago

•

253

upvoted a paper about 2 months ago

SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights

Paper • 2509.22944 • Published Sep 26 • 79

upvoted 2 articles about 2 months ago

view article

Article

Classement compar:IA : des votes des utilisateurs au classement participatif des modèles

• 

Nov 3

•

6

view article

Article

On the Shifting Global Compute Landscape

• 

Oct 29

•

53

New activity in kernels-community/triton_kernels 3 months ago

Implement make_opt_flags function for XPU

8

#5 opened 3 months ago by

YangKai0616

reacted to lysandre's post with 🚀 3 months ago

view post

Post

7328

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!

See translation

• 

• 
• 
• 6 replies

·

🚀

18

18

👍

9

9

🔥

6

6

+

Reply

New activity in kernels-community/triton_kernels 3 months ago

Kernel assertion errors on 5090 using generation with MXfp4 (gpt-oss) - (stable on 4090)

5

#1 opened 4 months ago by

cmp-nct

New activity in kernels-community/triton_kernels 4 months ago

Update torch-ext/triton_kernels/matmul_ogs_details/opt_flags.py

#3 opened 4 months ago by

marcsun13

Update build/torch-universal/triton_kernels/matmul_ogs_details/opt_flags.py

#2 opened 4 months ago by

marcsun13

liked a model 4 months ago

OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview

Image-Text-to-Text • 0.4B • Updated Aug 29 • 45.8k • 82

updated 2 models 4 months ago

kernels-community/triton_kernels

Updated Oct 27 • 2.85k • 7

hf-internal-testing/gpt-oss-20b-bf16

21B • Updated Aug 21 • 9

published a model 4 months ago

hf-internal-testing/gpt-oss-20b-bf16

21B • Updated Aug 21 • 9

liked 2 models 4 months ago

kernels-community/triton_kernels

Updated Oct 27 • 2.85k • 7

nunchaku-tech/nunchaku-qwen-image

Text-to-Image • Updated Nov 16 • 63.3k • 242

upvoted an article 5 months ago

view article

Article

Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training

• 
• 
• +3

Aug 8

•

89

New activity in openai/gpt-oss-20b 5 months ago

Don't think this works on 4090 with transformers, for me anyway

👀 2

19

#53 opened 5 months ago by

Fancellu

published an article 5 months ago

view article

Article

Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training

• 
• 
• +3

Aug 8

•

89

New activity in openai/gpt-oss-120b 5 months ago

Request: 4-bit GPTQ or AWQ quantized version of openai/gpt-oss-20b

🚀 ❤️ 14

12

#32 opened 5 months ago by

powtac

running mxfp4 on H100 using tranformers with triton_kernel: make_default_matmul_mxfp4_w_layout not found

5

#64 opened 5 months ago by

uillliu