Profile, fix and benchmark hybrid GPU-prefill and CPU/SIMD decoding, especially long-context KV handoff and coding/tool rounds. Use for backend kernels, batch/thread/MTP tuning, state-layout changes and performance qualification on shared-memory hosts.
rcarmo/llama-cpp
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 4
- GitHub stars
- 3
- GitHub forks
- 1
Install with an AI assistant
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/rcarmo/llama-cpp.Loading the repository README…
Skills in this repository
2 occupation categories · 75% classified
Showing 4 of 4 collected skills.
skill
occupation
description
updated
occupation
Software Developers
description
updated
occupation
unclassified
description
Opinionated app components building on top of ./ui primitives
updated
occupation
Software Developers
description
Guided workflow for adding a new model architecture to llama.cpp. Use when the user wants to add/port a new model architecture.
updated
occupation
Software Quality Assurance Analysts & Testers
description
Review llama.cpp changes against project conventions and common reviewer pitfalls before a PR. Use when the user wants to review a diff, branch, or PR.
updated
Showing 4 of 4 collected skills.