89 71 116

Aryan V S

a-r-r-o-w

a-r-r-o-w

AI & ML interests

computer vision, reinforcement learning

Recent Activity

reacted to gokaygokay's post with 🔥 16 days ago

FlashPack: Lightning-Fast Model Loading for PyTorch https://github.com/fal-ai/flashpack FlashPack — a new, high-throughput file format and loading mechanism for PyTorch that makes model checkpoint I/O blazingly fast, even on systems without access to GPU Direct Storage (GDS). With FlashPack, loading any model can be 3–6× faster than with the current state-of-the-art methods like accelerate or the standard load_state_dict() and to() flow — all wrapped in a lightweight, pure-Python package that works anywhere.

new activity about 2 months ago

huggingface/documentation-images:Add images/videos for productionizing diffusion articles

new activity about 2 months ago

huggingface/documentation-images:Add images/videos for productionizing diffusion articles

View all activity

Organizations

upvoted an article 2 months ago

Article

Make your ZeroGPU Spaces go brrr with ahead-of-time compilation

Sep 2

• 69

upvoted a collection 3 months ago

Tfree-HAT-7b-pretrained

Collection

Tokenizer free models based on Hierarchical Autoregressive Transformer (https://arxiv.org/abs/2501.10322) trained from scratch. • 2 items • Updated Aug 1 • 10

upvoted 3 articles 3 months ago

Article

From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels

Aug 18

• 87

Article

Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨

Jul 25

• 83

Article

Your Own GPU-Powered Image Generator with HF Jobs

•

Jul 31

• 25

upvoted 5 articles 4 months ago

Article

How to Run a Hugging Face Model in JAX (Part 1)

•

Jul 20

• 28

Article

Image compositing with diffusers

•

Jul 17

• 5

Article

Creating custom kernels for the AMD MI300

Jul 9

• 51

Article

How Much Power does a SOTA Open Video Model Use? ⚡🎥

and 2 others •

Jul 2

• 15

Article

Bringing Fusion Down to Earth: ML for Stellarator Optimization

•

Jul 2

• 75

upvoted a paper 5 months ago

Text-Aware Image Restoration with Diffusion Models

Paper • 2506.09993 • Published Jun 11 • 41

upvoted an article 5 months ago

Article

Groq on Hugging Face Inference Providers 🔥

Jun 16

• 43

upvoted 2 papers 5 months ago

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Paper • 2506.09350 • Published Jun 11 • 48

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

Paper • 2506.06276 • Published Jun 6 • 23

upvoted an article 5 months ago

Article

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

Jun 3

• 93

upvoted a paper 6 months ago

Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model

Paper • 2505.17561 • Published May 23 • 31

upvoted an article 7 months ago

Article

Tiny Agents: an MCP-powered agent in 50 lines of code

Apr 25

• 301

upvoted a collection 7 months ago

SkyReels-V2

Collection

Infinite-length Film Generative Model • 17 items • Updated Jun 14 • 59

upvoted 2 articles 7 months ago

Article

FramePack LoRA Experiment

•

Apr 19

• 22

Article

Gotchas in Tokenizer Behavior Every Developer Should Know

•

Apr 18

• 45

Aryan V S

AI & ML interests

Recent Activity

Organizations

a-r-r-o-w's activity

Make your ZeroGPU Spaces go brrr with ahead-of-time compilation

From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels

Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨

Your Own GPU-Powered Image Generator with HF Jobs

How to Run a Hugging Face Model in JAX (Part 1)

Image compositing with diffusers

Creating custom kernels for the AMD MI300

How Much Power does a SOTA Open Video Model Use? ⚡🎥

Bringing Fusion Down to Earth: ML for Stellarator Optimization

Groq on Hugging Face Inference Providers 🔥

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

Tiny Agents: an MCP-powered agent in 50 lines of code

FramePack LoRA Experiment

Gotchas in Tokenizer Behavior Every Developer Should Know