Marc Sun's picture

Marc Sun

marcsun13

·

AI & ML interests

LLM, Quantization, Training, Inference

Recent Activity

updated a Space 21 days ago

marcsun13/trackio

published a Space 21 days ago

marcsun13/trackio

new activity about 1 month ago

kernels-community/triton_kernels:Implement make_opt_flags function for XPU

View all activity

Organizations

upvoted 4 articles 3 months ago

Article

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

Aug 8

• 76

Article

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

Aug 5

• 503

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

Jul 29

• 190

Article

Fast LoRA inference for Flux with Diffusers and PEFT

Jul 23

• 48

upvoted 2 articles 4 months ago

Article

Transformers backend integration in SGLang

Jun 23

• 53

Article

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

Jun 19

• 90

upvoted a changelog 5 months ago

Changelog

New Inference Providers Dashboard

Jun 5

• 65

upvoted an article 5 months ago

Article

Fine-tuning Llama 2 70B using PyTorch FSDP

Sep 13, 2023

• 30

upvoted a collection 5 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 • 2

upvoted 2 articles 5 months ago

Article

The Transformers Library: standardizing model definitions

May 15

• 120

Article

Exploring Quantization Backends in Diffusers

May 21

• 44

upvoted a collection 5 months ago

EXL3 models

32 items • Updated 28 days ago • 38

upvoted 2 articles 6 months ago

Article

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

Apr 29

• 40

Article

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

By

and 3 others •

Apr 23

• 12

upvoted a collection 6 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 • 209

upvoted 2 articles 7 months ago

Article

Memory-efficient Diffusion Transformers with Quanto and Diffusers

Jul 30, 2024

• 68

Article

Welcome Llama 4 Maverick & Scout on Hugging Face!

Apr 5

• 145

upvoted a collection 7 months ago

Llama 4

Llama 4 release • 13 items • Updated Apr 29 • 648

upvoted an article 7 months ago

Article

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

Mar 18

• 42

upvoted an article 8 months ago

Article

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

Mar 12

• 467