PyPI
vllm-project/speculators
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
Apache-2.08 oct 2026 · métricas 2.10.0
Todas las etiquetas
Etiqueta del catálogo
#speculative-decoding
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.
9 registros
npm
withcatai/node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
MIT27 ago 2026 · métricas 2.10.0
crates.io · npm · PyPI
dphnAI/sonar
Large-scale LLM inference engine
AGPL-3.018 sept 2026 · métricas 2.10.0
PyPI · npm
youssofal/MTPLX
3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
Apache-2.015 sept 2026 · métricas 2.10.0
PyPI
ARahim3/mlx-dspark
Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.
MIT19 oct 2026 · métricas 2.10.0
PyPI · crates.io
FedericoTs/quantprobe
Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGUF on your exact hardware, self-calibrates, emits the exact llama.cpp command — or 'quantprobe auto' does it all. Falsification-tested laws; misses published at full size. pip install quantprobe
MIT19 oct 2026 · métricas 2.10.0
PyPI
asher/gmlx
Local inference platform for K/IQ-quant GGUF models on Apple Silicon
Licencia propia25 sept 2026 · métricas 2.10.0
npm
therealtimex/node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
MIT10 sept 2026 · métricas 2.10.0
npm · crates.io · Maven
arusatech/llama-cpp-pro
Llama cpp + CapacitorJS support
MIT15 sept 2026 · métricas 2.10.0