matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-20 12:47:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Revamp the dynamic library shim

Browse Source 
This switches the default llama.cpp to be CPU based, and builds the GPU variants
as dynamically loaded libraries which we can select at runtime.

This also bumps the ROCm library to version 6 given 5.7 builds don't work
on the latest ROCm library that just shipped.
This commit is contained in:
Daniel Hiltgen
2023-12-20 10:36:01 -08:00
parent 1d1eb1688c
commit 7555ea44f8
14 changed files with 272 additions and 280 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile.build
View File

@@ -3,7 +3,7 @@ FROM --platform=linux/amd64 ubuntu:20.04 AS base-amd64
ARG CUDA_VERSION=11.3.1-1
ARG CMAKE_VERSION=3.22.1
# ROCm only supports amd64
ARG ROCM_VERSION=5.7
ARG ROCM_VERSION=6.0
# Note: https://rocm.docs.amd.com/en/latest/release/user_kernel_space_compat_matrix.html
RUN apt-get update && \