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
27 repos
-
๐งฑ Experimental library for building inference engines
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
PantheonSim: GPU simulator for CUDA and ROCm. Run CUDA and HIP programs unmodified on a CPU, no GPU needed: simulated NVIDIA and AMD GPUs for development, teaching and CI.
-
Fork of Apache MXNet 2.0 โ runs legacy MXNet code on CUDA 13 / Blackwell (sm_120) GPUs and native Apple Silicon CPU.
-
NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.
-
A PyTorch native automated mega-kernel compiler
-
Two case studies: megakernels roughly on par with CUDA Graphs + PDL. Code and baselines for further research.
-
VoiceStudio is the open-source, fully-local ElevenLabs alternative โ voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
-
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
-
Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.
-
Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh
-
Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!
-
Open Source AI Accelerator Research Platform Standard / ๅผๆบๆจ็็ ็ฉถๅนณๅฐ
-
FlashInfer: Kernel Library for LLM Serving
-
A retargetable MLIR-based machine learning compiler and runtime toolkit.
-
CUDA Craftax-Classic: 7x faster RL training than JAX
-
A flyweight in situ visualization and analysis runtime for multi-physics HPC simulations
-
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
-
PyTorch native quantization for training and inference
-
High-Performance Cross-Platform Monte Carlo Renderer Based on LuisaCompute
-
The open-source AI voice studio. Clone, dictate, create.
-
Build configuration for PyCUDA
-
Throwaway staging: validate CUDA 13.3 prebuilt build leg