@aradotso/dflash-mlx-speculative-decoding

Lossless DFlash speculative decoding for MLX on Apple Silicon — 1.7–4x faster LLM inference using block diffusion drafting with target model verification.

View in AI SkillSafe app
Scanned · no findings
0 downloads
0 stars
0 demos
SKILL.md

Embed badges

Add these to your README to show the skill's verification status.

SkillSafe verified badge
Verified badge
[![SkillSafe verified badge](https://api.skillsafe.ai/v1/badge/@aradotso/dflash-mlx-speculative-decoding/verified)](https://skillsafe.ai/skill/@aradotso/dflash-mlx-speculative-decoding/)
Installs badge
Installs badge
[![Installs badge](https://api.skillsafe.ai/v1/badge/@aradotso/dflash-mlx-speculative-decoding/installs)](https://skillsafe.ai/skill/@aradotso/dflash-mlx-speculative-decoding/)
Scan badge
Scan badge
[![Scan badge](https://api.skillsafe.ai/v1/badge/@aradotso/dflash-mlx-speculative-decoding/scan)](https://skillsafe.ai/skill/@aradotso/dflash-mlx-speculative-decoding/)
Eval pass rate badge
Eval pass rate
[![Eval pass rate badge](https://api.skillsafe.ai/v1/badge/@aradotso/dflash-mlx-speculative-decoding/eval)](https://skillsafe.ai/skill/@aradotso/dflash-mlx-speculative-decoding/)