shtjwwshtjww/llm-inference-capacity-handbook
大模型推理案头手册（开源版）：给定 GPU 算力，一个模型能扛多少 QPS？三层模型 × 三面墙 × 排队论 × 开环压测
104
Stars0
Forks0
Open issues104
Watchers—
License—
LanguageSep 2, 2026
CreatedSep 2, 2026
Last pushed+0
Star growth · 1 dayNot enough data yet
Star growth · 7 daysNot enough data yet
Star growth · 30 days