writing-skills
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Explorar Skills
Despliegue y operaciones · SKILL.md
dparallel-diffusion-llm-parallel-decoding
dparallel-diffusion-llm-parallel-decodingEnable Diffusion Language Models to achieve 8.5x inference speedup (24-30 steps vs. 256) through certainty-forcing distillation that trains models to achieve simultaneous high confidence across multiple tokens. Use when optimizing inference latency for dLLM deployments.
Independent GitHub snapshot · Automated classification · Original documentation governs
Documentación de la Skill
GitHubCargando documentación desde el origen…