npm · crates.io
mlx-node/mlx-node
Keine Repository-Beschreibung veröffentlicht.
MIT16. Sept. 2026 · Metriken 2.10.0
Alle Tags
Katalog-Tag
#cuda
Alle Repositories im öffentlichen Register, die dieses Tag tragen — aus ihren GitHub-Topics oder den von ihren Paket-Registries veröffentlichten Schlagwörtern. Die Gesundheit wird nach derselben versionierten Methodik gemessen wie im übrigen Register.
111 Einträge
—
CVCUDA/CV-CUDA
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
Eigene Lizenz20. Okt. 2026 · Metriken 2.10.0
PyPI · crates.io
Egoist-Machines/LodeDB
World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated
Apache-2.016. Sept. 2026 · Metriken 2.10.0
crates.io · PyPI
avencera/speakrs
Speaker diarization in Rust with pyannote-level accuracy. 900–1940x realtime on NVIDIA GPUs, 430–910x on Apple Silicon.
Apache-2.018. Okt. 2026 · Metriken 2.10.0
crates.io
chelsea0x3b/cudarc
Safe rust wrapper around CUDA toolkit
Apache-2.018. Sept. 2026 · Metriken 2.10.0
crates.io
frames-sg/j2k
Rust JPEG 2000 / HTJ2K codec with CUDA and Metal GPU paths.
Eigene Lizenz30. Sept. 2026 · Metriken 2.10.0
PyPI
robodreamer/embodik
Prioritized inverse kinematics for many robot bodies: a C++ solver with Python bindings, collision and balance constraints, and an experimental CUDA batch whole-body solver.
Apache-2.019. Okt. 2026 · Metriken 2.10.0
—
CliMA/RRTMGP.jl
Fast, GPU-ready atmospheric radiative transfer in Julia: the RTE solver with RRTMGP correlated-k gas optics.
Apache-2.010. Sept. 2026 · Metriken 2.10.0
Go
hybridgroup/yzma
Go with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.
Eigene Lizenz9. Sept. 2026 · Metriken 2.10.0
Maven · npm
qxoticai/qxotic
AI sovereignty for the world's most trusted runtime.
Apache-2.019. Okt. 2026 · Metriken 2.10.0
crates.io · PyPI
abyo-software/s4
GPU-accelerated transparent compression S3-compatible storage gateway. Drop-in replacement for AWS S3 endpoints; cuts your S3 bill 50-80% with no app changes (Rust, nvCOMP, zstd).
Apache-2.018. Sept. 2026 · Metriken 2.10.0
npm · PyPI
invergent-ai/surogate
Train and serve LLMs at extreme speed and massive throughput.
Apache-2.012. Sept. 2026 · Metriken 2.10.0
NuGet
iyulab/lm-supply
.NET library for on-demand local AI model inference — zero bundled models, lazy loading, hardware-aware GPU/CPU selection, 10 task types including embeddings, generation, vision, and audio.
MIT10. Sept. 2026 · Metriken 2.10.0
Go
eitamring/gocudrv
CUDA driver API in pure Go, no cgo: loads libcuda at runtime, embeds PTX, JIT-compiles through the driver
MIT10. Sept. 2026 · Metriken 2.10.0
PyPI
nevenincs/vaultspec-rag
Search code and feature records by meaning through the command line or Model Context Protocol (MCP). Inference runs on your GPU.
MIT14. Sept. 2026 · Metriken 2.10.0
NuGet
ooples/AiDotNet.Tensors
The fastest .NET tensor library. Beats MathNet (6x), NumSharp (3200x), matches TorchSharp CPU - pure managed C# with hand-tuned AVX2/FMA SIMD kernels. Optional CUDA/OpenCL GPU acceleration.
Apache-2.06. Sept. 2026 · Metriken 2.10.0
PyPI
pjordanandrsn/experts4bit-qlora
Train and serve MoE models that do not fit in VRAM: fused 4-bit experts, QLoRA, CPU/NVMe offload, and fast inference on consumer NVIDIA GPUs.
MIT15. Sept. 2026 · Metriken 2.10.0
crates.io
santhreal/vyre
Make GPUs do branchy stuff fast.
Apache-2.09. Sept. 2026 · Metriken 2.10.0
npm
mybigday/whisper.node
An another Node binding of whisper.cpp to make same API with whisper.rn as much as possible.
MIT13. Sept. 2026 · Metriken 2.10.0
Go
sahandsafizadeh/qeep
Deep Learning framework in Go with Tensors, AutoGrad, and GPU acceleration
MIT18. Sept. 2026 · Metriken 2.10.0
crates.io · npm · Go +1
tree-sitter-grammars/tree-sitter-cuda
CUDA grammar for tree-sitter
MIT18. Sept. 2026 · Metriken 2.10.0
PyPI
varjoranta/turboquant-vllm
TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fallback.
MIT12. Sept. 2026 · Metriken 2.10.0
crates.io
frames-sg/jxr
JPEG XR decoder in Rust with optional Metal and CUDA backends
Eigene Lizenz21. Okt. 2026 · Metriken 2.10.0
PyPI
pjordanandrsn/grouped-nf4-gemm
Triton kernels for 4-bit MoE inference: grouped NF4/MXFP4 GEMM, INT4 GEMV, FP8 paged attention, and CPU/NVMe expert streaming.
MIT24. Sept. 2026 · Metriken 2.10.0
PyPI
PozzettiAndrea/comfy-env
CUDA dependency management and process isolation for ComfyUI custom nodes
MIT24. Aug. 2026 · Metriken 2.10.0
—
arrayfire/arrayfire
ArrayFire: a general purpose GPU library.
BSD-3-Clause18. Okt. 2026 · Metriken 2.10.0
PyPI
NVIDIA-Omniverse/ovstage
A C and Python library providing a shared, high-performance, vectorized, GPU-capable scene data substrate for OpenUSD data across Omniverse Libraries (physics, rendering, sensors, animation).
Eigene Lizenz15. Okt. 2026 · Metriken 2.10.0
PyPI
ROCm/hipBLAS
[DEPRECATED] Moved to ROCm/rocm-libraries repo
Eigene Lizenz28. Aug. 2026 · Metriken 2.10.0
PyPI
SHI-Labs/NATTEN
Fast Multi-dimensional Sparse Attention
MIT19. Sept. 2026 · Metriken 2.10.0
PyPI
RobTand/gridbook
Out-of-tree vLLM plugin and open format spec for NVFP4-CB / FP8-CB product-codebook weights — 2-6 bit-per-weight LLM quantization served on native Blackwell tensor cores.
Apache-2.018. Sept. 2026 · Metriken 2.10.0