Marc Sun

marcsun13's activity

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

upvoted 8 articles 5 days ago

view article

Article

Continuous batching from first principles

• 
• 
• +1

Nov 25, 2025

•

301

view article

Article

Diffusers welcomes FLUX-2

• 
• 
• +6

Nov 25, 2025

•

168

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

Dec 4, 2025

•

571

view article

Article

New in llama.cpp: Model Management

• 

Dec 11, 2025

•

105

view article

Article

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

• 
• 
• +4

25 days ago

•

111

view article

Article

NVIDIA brings agents to life with DGX Spark and Reachy Mini

• 
• 
• +1

7 days ago

•

46

view article

Article

Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architecture

• 

6 days ago

•

31

view article

Article

NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI

• 

6 days ago

•

38

liked a Space 5 days ago

Running

Reachy

70

Reachy Mini

🤖

70

All about Reachy Mini, from building to getting started

upvoted an article about 1 month ago

view article

Article

Transformers v5: Simple model definitions powering the AI ecosystem

• 
• 
• +2

Dec 1, 2025

•

270

upvoted a paper 2 months ago

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

Paper • 2509.22944 • Published Sep 26, 2025 • 79

upvoted 2 articles 2 months ago

view article

Article

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

• 

Nov 3, 2025

•

6

view article

Article

On the Shifting Global Compute Landscape

• 

Oct 29, 2025

•

55

New activity in kernels-community/triton_kernels 4 months ago

Implement make_opt_flags function for XPU

8

#5 opened 4 months ago by

YangKai0616

reacted to lysandre's post with 🚀 4 months ago

view post

Post

7510

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 4 months ago

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

5

#1 opened 5 months ago by

cmp-nct

New activity in kernels-community/triton_kernels 5 months ago

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

#3 opened 5 months ago by

marcsun13

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

#2 opened 5 months ago by

marcsun13

liked a model 5 months ago

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

Image-Text-to-Text • 0.4B • Updated Aug 29, 2025 • 30.7k • 82

updated a model 5 months ago

kernels-community/triton_kernels

Updated Oct 27, 2025 • 3.82k • 7