ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[model] update kt code (#9406)

Browse Source
This commit is contained in:
Yaowei Zheng
2025-11-05 15:27:22 +08:00
committed by GitHub
parent 56f45e826f
commit eaf963f67f
28 changed files with 108 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/inference/deepseek2_lora_sft_kt.yaml
View File

@@ -7,4 +7,4 @@ trust_remote_code: true
use_kt: true # use KTransformers as LoRA sft backend to inference
kt_optimize_rule: examples/kt_optimize_rules/DeepSeek-V2-Lite-Chat-sft-amx.yaml
cpu_infer: 32
chunk_size: 8192
chunk_size: 8192

2
examples/inference/deepseek3_kt.yaml
View File

@@ -6,4 +6,4 @@ trust_remote_code: true
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
chunk_size: 8192

2
examples/inference/deepseek3_lora_sft_kt.yaml
View File

@@ -7,4 +7,4 @@ trust_remote_code: true
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
chunk_size: 8192