llama2.c的一些常规操作

git clone https://github.com/karpathy/llama2.c.git
cd llama2.c
python export.py llama2_7b.bin --meta-llama path/to/llama/model/7B
python export.py llama2_7b_q80.bin --version 2 --meta-llama path/to/llama/model/7B
make runomp
OMP_NUM_THREADS=64 ./run llama2_7b.bin -n 40
OMP_NUM_THREADS
C:\Users\16079>wsl.exe -d Ubuntu-24.04 hkw@localhost:/mnt/c/Users/16079$ ollama run deepseek-r1:1.5b Error: llama runner process has terminated: exit status 127 hkw@localhost:/mnt/c/Users/16079$ ls /usr/local/cuda-12.x ls: cannot access '/usr/local/cuda-12.x': No such file or directory hkw@localhost:/mnt/c/Users/16079$ sudo apt install --reinstall cuda-toolkit-12-0 # 根据实际版本调整 [sudo] password for hkw: Reading package lists... Done Building dependency tree... Done Reading state information... Done N: Ignoring file 'ubuntu.sources.save.1' in directory '/etc/apt/sources.list.d/' as it has an invalid filename extension N: Ignoring file 'ubuntu.sources.save.2' in directory '/etc/apt/sources.list.d/' as it has an invalid filename extension E: Unable to locate package cuda-toolkit-12-0 hkw@localhost:/mnt/c/Users/16079$ ./ollama_llama_server -bash: ./ollama_llama_server: No such file or directory hkw@localhost:/mnt/c/Users/16079$ nvidia-smi # 查看驱动版本和GPU状态 Thu Mar 13 20:40:10 2025 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 565.75 Driver Version: 566.26 CUDA Version: 12.7 | |-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce RTX 4050 ... On | 00000000:01:00.0 Off | N/A | | N/A 42C P8 1W / 78W | 0MiB / 6141MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+---------
最新发布
03-14
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值