Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
15 repos
-
Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
-
CPU exercise: implement KV caching inside attention.
-
Morphology-adaptive muscle-driven locomotion via attention mechanisms
-
Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average speedup of 34.93x
-
FlashInfer: Kernel Library for LLM Serving
-
high-performance linear attention kernel library built on TileLang
-
🚀 Efficient implementations for emerging model architectures
-
Fast and memory-efficient exact attention
-
Build configuration for Flash Attention
-
Build configuration for Flash Attention 3
-
Build configuration for SageAttention
-
Build configuration for SageAttention 3
-
Official repository for Parallax (Parameterized Local Linear Attention)