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
21 repos
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
-
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
-
NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.
-
Distributed High-Performance Symbolic Regression in Julia
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Curated high-performance TIRx GPU kernels
-
Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
A high-performance and light-weight router for vLLM large scale deployment
-
A multi-framework neural network compiler lowering PyTorch, JAX, Flax, and Keras models to portable, high-performance GGML execution
-
★ 0 xeophon/sglangSGLang is a high-performance serving framework for large language models and multimodal models.
-
A curated list of resources for PufferLib, the high-performance reinforcement learning library.
-
High-Performance Symbolic Regression in Python and Julia
-
Performance-portable library for particle-based simulations
-
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
-
high-performance linear attention kernel library built on TileLang
-
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
-
High-Performance Cross-Platform Monte Carlo Renderer Based on LuisaCompute
-
Thousand Island is a pure Elixir socket server
-
high-performance inference and serving library for interactive autoregressive video and world models