[docs]: fix links to moved injection and Kimi-K2 native tutorials (#2223)

This commit is contained in:
Pratik Gandhi
2026-10-11 21:45:01 -07:00
committed by GitHub
parent 44fbb184d5
commit 6d836359a5
5 changed files with 6 additions and 6 deletions
+1 -1
View File
@@ -57,7 +57,7 @@ KTransformers is a research project focused on efficient inference and fine-tuni
* **Feb 15, 2025**: Longer Context (from 4K to 8K for 24GB VRAM) & Slightly Faster Speed (+15%, up to 16 Tokens/s), update [docs](./doc/en/DeepseekR1_V3_tutorial.md) and [online books](https://kvcache-ai.github.io/ktransformers/).
* **Feb 10, 2025**: Support Deepseek-R1 and V3 on single (24GB VRAM)/multi gpu and 382G DRAM, up to 3~28x speedup. For detailed show case and reproduction tutorial, see [here](./doc/en/DeepseekR1_V3_tutorial.md).
* **Aug 28, 2024**: Decrease DeepseekV2's required VRAM from 21G to 11G.
* **Aug 15, 2024**: Update detailed [tutorial](doc/en/injection_tutorial.md) for injection and multi-GPU.
* **Aug 15, 2024**: Update detailed [tutorial](doc/en/SFT/injection_tutorial.md) for injection and multi-GPU.
* **Aug 14, 2024**: Support llamfile as linear backend.
* **Aug 12, 2024**: Support multiple GPU; Support new model: mixtral 8\*7B and 8\*22B; Support q2k, q3k, q5k dequant on gpu.
* **Aug 9, 2024**: Support windows native.
+1 -1
View File
@@ -43,7 +43,7 @@ KTransformers 是一个专注于通过 CPU-GPU 异构计算实现大语言模型
* **2025 年 2 月 15 日**:更长上下文(24GB VRAM 从 4K 到 8K)& 速度稍快(+15%,最高 16 Tokens/s),更新[文档](./doc/en/DeepseekR1_V3_tutorial.md)和[在线手册](https://kvcache-ai.github.io/ktransformers/)
* **2025 年 2 月 10 日**:支持 Deepseek-R1 和 V3 在单 GPU(24GB VRAM)/多 GPU 和 382GB DRAM 上运行,速度提升高达 3~28 倍。详细案例展示和复现教程请参见[这里](./doc/en/DeepseekR1_V3_tutorial.md)
* **2024 年 8 月 28 日**:将 DeepseekV2 所需的 VRAM 从 21GB 降低到 11GB
* **2024 年 8 月 15 日**:更新了关于注入和多 GPU 的详细[教程](doc/en/injection_tutorial.md)
* **2024 年 8 月 15 日**:更新了关于注入和多 GPU 的详细[教程](doc/en/SFT/injection_tutorial.md)
* **2024 年 8 月 14 日**:支持 llamfile 作为线性后端
* **2024 年 8 月 12 日**:支持多 GPU;支持新模型:mixtral 8\*7B 和 8\*22B;支持 GPU 上的 q2k、q3k、q5k 去量化
* **2024 年 8 月 9 日**:支持 Windows 原生环境
+1 -1
View File
@@ -1,5 +1,5 @@
# KTransformers+SGLang Inference Deployment
Please Note This is Quantization Deployment. For Native Kimi K2 Thinking deployment please refer to [here](./Kimi-K2-Thinking-Native.md).
Please Note This is Quantization Deployment. For Native Kimi K2 Thinking deployment please refer to [here](./kt-kernel/Kimi-K2-Thinking-Native.md).
## Installation
+1 -1
View File
@@ -1,7 +1,7 @@
# Muti-GPU
Assume you have read the [Injection Tutorial](./injection_tutorial.md) and have a basic understanding of how to inject a model. In this tutorial, we will show you how to use KTransformers to run a model on multiple GPUs.
Assume you have read the [Injection Tutorial](./SFT/injection_tutorial.md) and have a basic understanding of how to inject a model. In this tutorial, we will show you how to use KTransformers to run a model on multiple GPUs.
If you have multiple GPUs, you can set the device for each module to different GPUs.
DeepseekV2-Chat got 60 layers, if we got 2 GPUs, we can allocate 30 layers to each GPU. Complete multi GPU rule examples [here](https://github.com/kvcache-ai/ktransformers/blob/main/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu.yaml).
+2 -2
View File
@@ -38,7 +38,7 @@
- ✅ **带 AMX 的 Intel CPU**:已支持(基于转换为 INT4/INT8 格式的权重)
- ✅ **通用 CPU(llamafile 后端)**:已支持(基于 GGUF 格式的权重)
- ✅ **带 BLIS 的 AMD CPU**:已支持(int8 的 prefill 和 decode)
- ✅ **Kimi-K2 原生 INT4(RAWINT4)**:支持 AVX512 CPU(CPU-GPU 共享 INT4 权重)- [使用指南](../doc/en/Kimi-K2-Thinking-Native.md)
- ✅ **Kimi-K2 原生 INT4(RAWINT4)**:支持 AVX512 CPU(CPU-GPU 共享 INT4 权重)- [使用指南](../doc/en/kt-kernel/Kimi-K2-Thinking-Native.md)
## 特性
@@ -321,7 +321,7 @@ python -m sglang.launch_server \
- **`kt-method`**:根据 CPU 能力和权重格式选择:
- `AMXINT4`:在 AMX CPU 上 INT4 量化时具有最佳性能(但可能对某些模型有较大精度影响,例如 Qwen3-30B-A3B)
- `AMXINT8`:在 AMX CPU 上提供更高精度的 INT8 量化方案
- `RAWINT4`:CPU 和 GPU 共享原生 INT4 权重(仅限 AMX 后端,目前仅支持 Kimi-K2-Thinking 模型)。详见 [Kimi-K2-Thinking 原生推理教程](../doc/en/Kimi-K2-Thinking-Native.md)。
- `RAWINT4`:CPU 和 GPU 共享原生 INT4 权重(仅限 AMX 后端,目前仅支持 Kimi-K2-Thinking 模型)。详见 [Kimi-K2-Thinking 原生推理教程](../doc/en/kt-kernel/Kimi-K2-Thinking-Native.md)。
- `LLAMAFILE`:基于 AVX2/AVX512 的通用 CPU 后端,性能较 AMX 略低,但适用范围更广
- **`kt-cpuinfer`**:设置为 **物理核数**(不是线程数)。