Stars
TensorDict is a pytorch dedicated tensor container.
PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
S-SIM reward alignment test via f5-tts
Anthropic's original performance take-home, now open for you to try!
CUDA Tile IR is an MLIR-based intermediate representation and compiler infrastructure for CUDA kernel optimization, focusing on tile-based computation patterns and optimizations targeting NVIDIA te…
Simple and fast parallel scan over sequences of tensors, with any binary associative function you specify, for PyTorch (Franz A. Heinsen, 2024)
HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform
Tinymist [ˈtaɪni mɪst] is an integrated language service for Typst [taɪpst].
A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation
Crowd Sourced Emotional Multimodal Actors Dataset (CREMA-D)
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Croissant is a high-level format for machine learning datasets that brings together four rich layers.
A machine learning compiler for GPUs, CPUs, and ML accelerators
Machine learning metrics for distributed, scalable PyTorch applications.
Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.
TTS model capable of streaming conversational audio in realtime.
a small build system with a focus on speed
A C++ data container replicating std::stack functionality but with better performance than standard library containers in a stack context.
A single producer single consumer lock free queue that utilizes copy / move assignment to transfer messages. Achieves a top performance, faster than many of the leading SPSC queues.
A fast multi-producer, multi-consumer lock-free concurrent queue for C++11
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support
Code for the paper "Training Diffusion Models with Reinforcement Learning"