Repository
guqiong96/Lvllm agent skills
- skills
- 3
- GitHub stars
- 465
GitHub description: “LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, supporting hybrid inference for MOE large models.”
- Stars
- 465 (41 forks)
- Licence
- Apache-2.0
- Last push
- Sep 2026
- Created
- Sep 2025
- Homepage
- space.bilibili.com/625367168
- hybrid
- inference
- model
- moe
- numa
- parallelism
- vllm
- cpu
- decode
- gpu
- prefill
Install all skills
npx skills add guqiong96/LvllmAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in guqiong96/Lvllm, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Fetch and diagnose vLLM Buildkite CI failure logs. An agent skill from guqiong96/Lvllm. | guqiong96/ | 465 | 2 repos | ~349 | Automated safety check: Pass | Apache-2.0 | 18 days ago |
| 2 | Build, debug, and interpret vLLM GPU kernel microbenchmarks for CUDA, Triton, and CuteDSL, including CUPTI timing, correctness checks, generated-code inspection, multi-GPU measurements, and SOL… | guqiong96/ | 465 | 2 repos | ~1.5k | Automated safety check: Pass | Apache-2.0 | 18 days ago |
| 3 | Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation. | guqiong96/ | 465 | 1 repo | ~831 | Automated safety check: Pass | Apache-2.0 | 18 days ago |
Questions, answered from the data.
What is the best skill in guqiong96/Lvllm?
CI Fails Buildkite from guqiong96/Lvllm ranks first of the 3 skills in guqiong96/Lvllm listed here, with the highest score: its repository has 465 GitHub stars, 2 other GitHub owners carry a copy, its SKILL.md loads about 349 tokens and it passes the automated safety check with no findings. Next come Kernel Microbenchmark and Triton Kernel Writing.
Are the skills in guqiong96/Lvllm official?
None yet. All 3 skills in guqiong96/Lvllm listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from guqiong96/Lvllm?
Run npx skills add guqiong96/Lvllm in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.