#gpu

PyPI capacity-planning CLI for LLM deployment. pip install chimeraforge.

Pure Go FFI for WebGPU - CGO-free GPU access via wgpu-native bindings

Zero-CGO WebGPU bindings for Go — GPU-accelerated graphics and compute in pure Go

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.

Safe rust wrapper around CUDA toolkit

CUDA ecosystem wrappers for Rust

Classifies GPUs based on their 3D rendering benchmark score allowing the developer to provide sensible default settings for graphically intensive applications.

A JAX backend for Apple Metal Performance Shaders (MPS), enabling GPU-accelerated JAX computations on Apple Silicon.

Suite of python packages for multiparticle simulations of particle accelerators.

Fast non-allocating calculations of gradients, Jacobians, and Hessians with sparsity support

LoRA post-training for open-weight models: SFT, GRPO, and on-policy distillation. Describe a run in TOML; Flash allocates a GPU, trains, streams checkpoints, and serves the adapter.

Rigid body fitting of atomic strucures in cryo-electron microscopy density maps