# shtjww/llm-inference-capacity-handbook

<https://repo.masters-masters.com/en/repos/shtjww/llm-inference-capacity-handbook>

[Home](https://repo.masters-masters.com/en) › [shtjww](https://repo.masters-masters.com/en/owners/shtjww) › [llm-inference-capacity-handbook](https://repo.masters-masters.com/en/repos/shtjww/llm-inference-capacity-handbook)

shtjww/llm-inference-capacity-handbook has 185 stars on GitHub. Its RepoMasters card: Prototype tier. 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 ×…

| Field | Value |
| --- | --- |
| Owner | [shtjww](https://repo.masters-masters.com/en/owners/shtjww) |
| Stars | 185 |
| Forks | 0 |
| Language | No language |
| License | None |
| Created | 2026 |
| Topics | capacity-planning, gpu, llm-inference, llmops, queueing-theory, vllm |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [shtjww/llm-inference-capacity-handbook](https://github.com/shtjww/llm-inference-capacity-handbook) |

## Repository

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

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.