Marc Sun's picture

Marc Sun

marcsun13

·

AI & ML interests

LLM, Quantization, Training, Inference

Recent Activity

new activity about 19 hours ago

kernels-community/triton_kernels:Kernel assertion errors on 5090 using generation with MXfp4 (gpt-oss) - (stable on 4090)

liked a model about 19 hours ago

kernels-community/triton_kernels

liked a model about 23 hours ago

nunchaku-tech/nunchaku-qwen-image

View all activity

Organizations

upvoted an article 13 days ago

Article

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

By

and 4 others •

13 days ago

• 50

upvoted an article 16 days ago

Article

Welcome GPT OSS, the new open-source model family from OpenAI!

By

and 11 others •

16 days ago

• 467

upvoted 2 articles 23 days ago

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

By

and 4 others •

23 days ago

• 156

Article

Fast LoRA inference for Flux with Diffusers and PEFT

By

and 1 other •

29 days ago

• 45

upvoted an article about 2 months ago

Article

Transformers backend integration in SGLang

By

and 4 others •

Jun 23

• 52

upvoted an article 2 months ago

Article

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

By

and 4 others •

Jun 19

• 83

upvoted a changelog 3 months ago

Changelog

New Inference Providers Dashboard

Jun 5

• 62

upvoted an article 3 months ago

Article

Fine-tuning Llama 2 70B using PyTorch FSDP

By

and 3 others •

Sep 13, 2023

• 29

upvoted a collection 3 months ago

Flux quantized checkpoints

This collection regroups quantized flux checkpoints that we used in this blogpost: https://huggingface.co/blog/diffusers-quantization • 5 items • Updated May 21 • 1

upvoted 2 articles 3 months ago

Article

The Transformers Library: standardizing model definitions

By

and 3 others •

May 15

• 117

Article

Exploring Quantization Backends in Diffusers

By

and 2 others •

May 21

• 40

upvoted a collection 3 months ago

EXL3 models

28 items • Updated 18 days ago • 34

upvoted 2 articles 4 months ago

Article

Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs

By

and 8 others •

Apr 29

• 39

Article

🔥 Announcing FLUX-Juiced: The Fastest Image Generation Endpoint (2.6 times faster)!

By

and 3 others •

Apr 23

• 11

upvoted a collection 4 months ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 10 • 208

upvoted an article 4 months ago

Article

Memory-efficient Diffusion Transformers with Quanto and Diffusers

By

and 1 other •

Jul 30, 2024

• 68

upvoted an article 5 months ago

Article

Welcome Llama 4 Maverick & Scout on Hugging Face!

By

and 6 others •

Apr 5

• 146

upvoted a collection 5 months ago

Llama 4

Llama 4 release • 13 items • Updated Apr 29 • 609

upvoted 2 articles 5 months ago

Article

NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets

By

and 4 others •

Mar 18

• 41

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

By

and 3 others •

Mar 12

• 453