JeffyLapter

> 哥，我这里也是 0.2.1 版本。一直报错如下，都不知道怎么回事。 Building wheels for collected packages: ktransformers Building wheel for ktransformers (pyproject.toml) ... done Created wheel for ktransformers: filename=ktransformers-0.2.1-cp310-cp310-linux_x86_64.whl size=28304186 sha256=464a7862e6d69804b26bb40cd8681e2fc3883513a2db026d01c3e0b147b0d430 Stored in directory: /root/.cache/pip/wheels/ed/7a/7a/f8905ab90c6c356c64ba6284fa2ce0cf84c5610639299afa81 WARNING: Built...

> 直接这样运行速度快了。 > > ``` > numactl -N 1 -m 1 python ./ktransformers/local_chat.py --model_path /data/model/models--deepseek-ai--DeepSeek-R1/snapshots/8a58a132790c9935686eb97f042afa8013451c9f/ --gguf_path /data/gguf_model/DeepSeek-R1-Q4_K_M --optimize_rule_path /data/ktransformers/ktransformers/optimize/optimize_rules/DeepSeek-R1-Chat.yaml --cpu_infer 30 --max_new_tokens 1000 > ``` > > 这里面DeepSeek-R1-Chat.yaml的配置就是DeepSeek-V3-Chat.yaml中的复制版本 > >...

> > 直接这样运行速度快了。 > > ``` > > numactl -N 1 -m 1 python ./ktransformers/local_chat.py --model_path /data/model/models--deepseek-ai--DeepSeek-R1/snapshots/8a58a132790c9935686eb97f042afa8013451c9f/ --gguf_path /data/gguf_model/DeepSeek-R1-Q4_K_M --optimize_rule_path /data/ktransformers/ktransformers/optimize/optimize_rules/DeepSeek-R1-Chat.yaml --cpu_infer 30 --max_new_tokens 1000 > > ``` > >...