kvcache-ai/ktransformers
1
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-20 14:29:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update installation instructions

Browse Source
This commit is contained in:
Peilin Li
2025-11-04 23:06:05 +08:00
committed by GitHub
parent 501b114863
commit 4f9940700e
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
doc/en/KTransformers-Fine-Tuning_User-Guide.md
View File

@@ -120,11 +120,11 @@ git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
cd LLaMA-Factory
pip install -e ".[torch,metrics]" --no-build-isolation
# 3. Install the KTransformers wheel that matches your Torch and Python versions (Note: The CUDA version can differ from that in the wheel filename.)
# 3. Install the KTransformers wheel that matches your Torch and Python versions, from https://github.com/kvcache-ai/ktransformers/releases/tag/v0.4.1 (Note: The CUDA version can differ from that in the wheel filename.)
pip install ktransformers-0.4.1+cu128torch28fancy-cp310-cp310-linux_x86_64.whl
# 4. Install flash-attention, download the corresponding file based on your Python and Torch versions from: https://github.com/Dao-AILab/flash-attention/releases
pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu12torch2.8cxx11abiTRUE-cp310-cp310-linux_x86_64.whl
pip install flash_attn-2.8.3+cu12torch2.8cxx11abiTRUE-cp310-cp310-linux_x86_64.whl
# abi=True/False can find from below
# import torch
# print(torch._C._GLIBCXX_USE_CXX11_ABI)
@@ -291,4 +291,4 @@ chunk_size: 8192
By integrating **KTransformers LoRA fine-tuning** into **LLaMA-Factory**, we provide a practical guide for efficient training and deployment of MoE LLMs. KT brings cutting-edge optimizations (DeepSeek/Qwen/Kimi support with AMX-accelerated kernels), and LoRA enables customization under very low GPU memory. LLaMA-Factory offers a friendly, unified interface.
This integration (akin to Unsloth-style speedups) means even models with tens to hundreds of billions of parameters can be fine-tuned and deployed with low latency on commodity hardware. You get **memory savings, speed-ups, and usability** together. We encourage you to try LLaMA-Factory + KT for your next MoE project and follow this guide. Feedback is welcome!
This integration (akin to Unsloth-style speedups) means even models with tens to hundreds of billions of parameters can be fine-tuned and deployed with low latency on commodity hardware. You get **memory savings, speed-ups, and usability** together. We encourage you to try LLaMA-Factory + KT for your next MoE project and follow this guide. Feedback is welcome!