Todas las etiquetas
Etiqueta del catálogo

#quantization

Todos los repositorios del registro público que llevan esta etiqueta, procedente de sus topics de GitHub o de las palabras clave que publican sus registros de paquetes. La salud se mide con la misma metodología versionada que el resto del registro.

47 registros
Con la etiqueta «quantization»Ordenado por índice de salud
PyPI
67Buenoíndice de salud
google-ai-edge/LiteRT-CLI
A convenient CLI to streamline LiteRT related development workflows, including converting, quantizing, compiling, managing, running, benchmarking and visualizing LiteRT (TFLite) models on various hardwares (CPU / GPU / NPU) across platforms (desktop, mobile or cloud).
Python★ 41↓ 80/mes8 sept 2026
Apache-2.08 sept 2026 · métricas 2.10.0
PyPI
67Buenoíndice de salud
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.
Python★ 2↓ 3717/mes24 sept 2026
MIT24 sept 2026 · métricas 2.10.0
PyPI
65Buenoíndice de salud
SYSTRAN/faster-whisper
Faster Whisper transcription with CTranslate2
Python★ 25.4K↓ 8.7M/mes16 sept 2026
MIT16 sept 2026 · métricas 2.10.0
PyPI
65Buenoíndice de salud
asher/gmlx
Local inference platform for K/IQ-quant GGUF models on Apple Silicon
Python★ 31↓ 2075/mes25 sept 2026
Licencia propia25 sept 2026 · métricas 2.10.0
PyPI
63Moderadoíndice de salud
jagmarques/nexusquant
Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.
Python★ 2516 jul 2026
Licencia propia16 jul 2026 · métricas 2.10.0
PyPI
62Moderadoíndice de salud
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.
Python · Cuda★ 12↓ 1474/mes18 sept 2026
Apache-2.018 sept 2026 · métricas 2.10.0
PyPI
60Moderadoíndice de salud
manunicholasjacob/llama-roofline
Is your llama.cpp decode memory-bandwidth-bound? Find out in one command.
Python★ 1↓ 12.4K/mes13 oct 2026
MIT13 oct 2026 · métricas 2.10.0
PyPI
59Moderadoíndice de salud
jjang-ai/jangq
JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon
Python · Swift★ 225↓ 1557/mes13 sept 2026
Sin licencia13 sept 2026 · métricas 2.10.0
PyPI · npm · crates.io
54Moderadoíndice de salud
JunHwan-Kwon/deepbom
Local static analysis and evidence generation for deployed AI model artifacts
JavaScript · Rust★ 2↓ 8091/mes21 oct 2026
Apache-2.021 oct 2026 · métricas 2.10.0
npm
54Moderadoíndice de salud
mkbabb/value.js
CSS value units for color, length, angles, & c.
TypeScript★ 0↓ 156/mes12 sept 2026
MIT12 sept 2026 · métricas 2.10.0
crates.io
42Débilíndice de salud
RecursiveIntell/turbo-quant
Experimental Rust vector-compression sidecars implementing TurboQuant (ICLR 2026), PolarQuant and QJL research primitives, with exact reranking and workload-scoped benchmark receipts.
Rust · Python★ 26↓ 2127/mes20 oct 2026
MIT20 oct 2026 · métricas 2.10.0
npm
42Débilíndice de salud
stfurkan/bitgpu
Fast WebGPU runtime for 1-bit (binary-weight) LLMs in the browser. Bit-exact, zero runtime dependencies.
TypeScript · WGSL · Python★ 27↓ 204/mes14 sept 2026
MIT14 sept 2026 · métricas 2.10.0
PyPI
38Débilíndice de salud
fermionresearch/phonon
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
Python★ 25820 oct 2026
Apache-2.020 oct 2026 · métricas 2.10.0
PyPI
22En riesgoíndice de salud
nactttch/g2n
A torch.compile backend that pays attention: custom FX fusion passes, a Triton LayerNorm kernel, and a persistent compile cache. Apache-2.0 free core of the g2n platform.
Python★ 0↓ 2377/mes15 sept 2026
Apache-2.015 sept 2026 · métricas 2.10.0
PyPI
19Críticoíndice de salud
blue-oil/blueoil
Bring Deep Learning to small devices
Python · C++★ 24711 sept 2026
Apache-2.011 sept 2026 · métricas 2.10.0