Liu Zewen
@aidless
LLM Evaluation & Reliability — auditing the judges, gates and agent runtimes that decide whether a model actually improved.
Shandong, China On GitHub since March 2022
2
Published Tools
0
Total Stars
0
Weekly Downloads
2
GitHub Followers
114
Public Repos
100/100
Avg Security
Published Tools
2 Skillsacross 1 categoryaidless
A
Zero-dependency LLM deployment feasibility + roofline analyzer: run-worthiness, bandwidth-vs-compute bottleneck, batch scaling; refuses unanswerable capacity questions instead of printing fake tok/s
...moreSkillai-ml
1 dir
aidless
A
LLM serving benchmark harness and release gate: TTFT / TPOT / throughput / stability, CI-ready
Skillai-ml
1 dir