OpenBMB / ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.
https://ollama.com
MIT License
11 stars 5 forks source link

Issue with compiling OpenBMB's ollama fork #11

Open rchen19 opened 1 month ago

rchen19 commented 1 month ago

What is the issue?

Building on Ubuntu 20.04.6 LTS (GNU/Linux 5.4.0-169-generic x86_64):

go generate ./... seems to work, but go build . gives:

# github.com/ollama/ollama/gpu
gpu/amd_linux.go:162:19: undefined: RocmComputeMin
gpu/amd_linux.go:232:20: undefined: IGPUMemLimit
gpu/amd_linux.go:253:19: undefined: rocmMinimumMemory

nccv -V gives:

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Jun__8_16:49:14_PDT_2022
Cuda compilation tools, release 11.7, V11.7.99
Build cuda_11.7.r11.7/compiler.31442593_0

Attaching full terminal output for in txt file:

terminaloutput.txt

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

No response