---
title: "rtk vs vllm-ascend"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/rtk-ai-rtk-vs-vllm-project-vllm-ascend"
tools: ["rtk-ai-rtk", "vllm-project-vllm-ascend"]
---

# rtk vs vllm-ascend

Neutral, constraint-first comparison with live GitHub stats.

| | [rtk](/tools/rtk-ai-rtk.md) | [vllm-ascend](/tools/vllm-project-vllm-ascend.md) |
| --- | --- | --- |
| Tagline | CLI proxy reducing LLM token consumption by 60-90% | Community maintained hardware plugin for vLLM on Ascend |
| Stars | 69,302 | 2,376 |
| Forks | 4,297 | 1,551 |
| Open issues | 1,509 | 2,324 |
| Language | Rust | C++ |
| License | Apache-2.0 | Apache-2.0 |
| Categories | Inference & Serving, Developer Tools | Inference & Serving |

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=rtk-ai-rtk`](/api/graphcanon/graph?tool=rtk-ai-rtk)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_