kvcache-ai/ktransformers
1
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-20 22:39:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

[docs]: add kt-cli doc and update corresponding website (#1768)

Browse Source
This commit is contained in:
ZiWei Yuan
2025-12-29 23:06:22 +08:00
committed by GitHub
parent 9539ab91eb
commit b096b01fbc
5 changed files with 50 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
kt-kernel/README.md
View File

@@ -32,6 +32,10 @@ High-performance kernel operations for KTransformers, featuring CPU-optimized Mo
- ✅ **Kimi-K2 Native INT4 (RAWINT4)**: Supported on AVX512 CPUs (CPU-GPU shared INT4 weights) - [Guide](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/Kimi-K2-Thinking-Native.md)
- ✅ **FP8 weights (e.g., MiniMax-M2.1)**: Supported on AVX512 CPUs (CPU-GPU shared FP8 weights) - [Guide](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/MiniMax-M2.1-Tutorial.md)
**KT-CLI**
We are developing a simpler way to use KTransformers. Check out the [KT-CLI Guide](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/kt-cli.md) for more details.
## Features
- **CPU-Optimized MoE Kernels**: High-throughput MoE expert kernels optimized for instruction sets.