diffusers-ascend-pipeline

diffusers-ascend-pipeline is an MLOps & model serving skill for AI agents, published by ascend-ai-coding in the awesome-ascend-skills repository on GitHub. Skillspace rates diffusers-ascend-pipeline C (74/100) and it passed the safety scan; the rating is based on static analysis only.

Diffusers Pipeline 推理指南，用于华为昇腾 NPU。覆盖环境预检、通用 Pipeline 推理（图像/视频模型）、内存优化（CPU offload、attention slicing、VAE slicing）、LoRA 加载与融合、多卡推理和按版本检索 Diffusers API。用户一旦提到在昇腾 NPU 上运行 FLUX、SDXL、Wan、CogVideoX 等 Diffusers 推理，或需要排查推理参数、显存优化、LoRA 接入、Pipeline API 路径时，就应使用此 skill。

Grade
C
Quality
74 / 100
Safety
Passed
GitHub stars
136

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubascend-ai-coding/awesome-ascend-skills

Our review

Architecture
88 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

More MLOps & model serving skills

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.