Open source / #22257
Open source
shtjww/llm-inference-capacity-handbook
GitHub · shtjww · 16 days ago · 20 points
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
Source and ranking details
- Source adapter
- github-search
- Source weight
- 2
- Points
- 20
- Age
- 391.2 h
- Stored score
- 0.00045
- Current score
- 0.00045
- First seen
- 2026-09-05T08:37:05.904Z
Newsletter
Get practical AI engineering notes
Receive source-checked analysis of models, agents, evaluation, retrieval, and production reliability. Sent only when there is useful work to share.