vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-28 11:49:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Update SFT Installation Guide for KimiK2

Browse source 
Added installation instructions and usage examples for KimiK2.
This commit is contained in:
Peilin Li 2025-11-06 17:34:21 +08:00 • committed by GitHub
parent 3e0f72f7ee
commit 803e645bc1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
doc/en/SFT_Installation_Guide_KimiK2.md
View file

@ -42,7 +42,7 @@ pip install custom_flashinfer/
## Download Model
Download the official KIMI weights. If the weights are in FP8 format, please refer to https://github.com/kvcache-ai/ktransformers/pull/1559 to convert them to BF16 weights.
Download the official KIMI weights. If the weights are in FP8 format, please refer to [convert_kimi_k2_fp8_to_bf16_cpu.py](https://github.com/kvcache-ai/ktransformers/blob/main/kt-kernel/scripts/convert_kimi_k2_fp8_to_bf16_cpu.py) to convert them to BF16 weights.
## How to start
@ -131,4 +131,5 @@ use_kt: true # use KTransformers as LoRA sft backend to inference
kt_optimize_rule: examples/kt_optimize_rules/DeepSeek-V3-Chat-sft-amx-multi-gpu.yaml
cpu_infer: 32
chunk_size: 8192
```
```