Skip to content

Commit a8669af

Browse files
authored
docs: update readme document.
1 parent 508d715 commit a8669af

File tree

2 files changed

+14
-5
lines changed

2 files changed

+14
-5
lines changed

README.md

Lines changed: 7 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -29,8 +29,10 @@ limitations under the License. -->
2929

3030

3131
### 📢 News
32-
- 🎉 We recently have released our [xLLM Technical Report](https://arxiv.org/abs/2510.14686) on arXiv, providing comprehensive technical blueprints and implementation insights.
33-
32+
- 2025-12-05: 🎉 We now support high-performance inference for the [GLM-4.5/GLM-4.6](https://github.com/zai-org/GLM-4.5/blob/main/README_zh.md) series models.
33+
- 2025-12-05: 🎉 We now support high-performance inference for the [VLM-R1](https://github.com/om-ai-lab/VLM-R1) model.
34+
- 2025-12-05: 🎉 We build hybrid KV cache management based on [Mooncake](https://github.com/kvcache-ai/Mooncake), supporting global KV cache management with intelligent offloading and prefetching.
35+
- 2025-10-16: 🎉 We recently have released our [xLLM Technical Report](https://arxiv.org/abs/2510.14686) on arXiv, providing comprehensive technical blueprints and implementation insights.
3436

3537
## 1. Project Overview
3638

@@ -112,6 +114,8 @@ Supported models list:
112114
- Qwen2.5-VL
113115
- Qwen3 / Qwen3-MoE
114116
- Qwen3-VL / Qwen3-VL-MoE
117+
- GLM4.5 / GLM4.6
118+
- VLM-R1
115119

116120
---
117121

@@ -244,4 +248,4 @@ If you think this repository is helpful to you, welcome to cite us:
244248
journal={arXiv preprint arXiv:2510.14686},
245249
year={2025}
246250
}
247-
```
251+
```

README_zh.md

Lines changed: 7 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,10 @@ limitations under the License. -->
2828

2929
### 📢 新闻
3030

31-
- 我们最近在 arXiv 上发布了我们的 [xLLM 技术报告](https://arxiv.org/abs/2510.14686),提供了全面的技术蓝图和实施见解。
31+
- 2025-12-05: 🎉 我们支持了[GLM-4.5/GLM-4.6](https://github.com/zai-org/GLM-4.5/blob/main/README_zh.md)系列模型.
32+
- 2025-12-05: 🎉 我们支持了[VLM-R1](https://github.com/om-ai-lab/VLM-R1) 模型.
33+
- 2025-12-05: 🎉 我们基于[Mooncake](https://github.com/kvcache-ai/Mooncake)构建了混合 KV 缓存管理机制,支持具备智能卸载与预取能力的全局 KV 缓存管理。
34+
- 2025-10-16: 🎉 我们最近在 arXiv 上发布了我们的 [xLLM 技术报告](https://arxiv.org/abs/2510.14686),提供了全面的技术蓝图和实施见解。
3235

3336
## 1. 简介
3437

@@ -107,6 +110,8 @@ xLLM 提供了强大的智能计算能力,通过硬件系统的算力优化与
107110
- Qwen2.5-VL
108111
- Qwen3 / Qwen3-MoE
109112
- Qwen3-VL / Qwen3-VL-MoE
113+
- GLM-4.5 / GLM-4.6
114+
- VLM-R1
110115

111116
---
112117

@@ -249,4 +254,4 @@ python setup.py bdist_wheel
249254
journal={arXiv preprint arXiv:2510.14686},
250255
year={2025}
251256
}
252-
```
257+
```

0 commit comments

Comments
 (0)