GitLab

Refine debug logging for llm

Debug logging on init failure

This wires up logging in llama.cpp to always go to stderr, and also
turns up logging if OLLAMA_DEBUG is set.

fix: remove overwritten model layers

Make CPU builds parallel and customizable AMD GPUs

Probe GPUs before backend init

Detect potential error scenarios so we can fallback to CPU mode without
hitting asserts.

The linux build now support parallel CPU builds to speed things up.
This also exposes AMD GPU targets as an optional setting for advaced
users who want to alter our default set.

Combine the 2 Dockerfiles and add ROCm

This renames Dockerfile.build to Dockerfile, and adds some new stages
to support 2 modes of building - the build_linux.sh script uses
intermediate stages to extract the artifacts for ./dist, and the default
build generates a container image usable by both cuda and rocm cards.
This required transitioniing the x86 base to the rocm image to avoid
layer bloat.

if create overrides a manifest, first add the older manifest's layers to
the delete map so they can be cleaned up

More WSL paths

Switch to local dlopen symbols

Fix CPU-only build under Android Termux enviornment.

Update gpu.go initGPUHandles() to declare gpuHandles variable before
reading it. This resolves an "invalid memory address or nil pointer
dereference" error.

Update dyn_ext_server.c to avoid setting the RTLD_DEEPBIND flag under
__TERMUX__ (Android).

fix show handler

api: add model for all requests

ci: update setup-go action

prefer using req.Model and fallback to req.Name

Mechanical switch from log to slog

install: pin fedora to max 37

A few obvious levels were adjusted, but generally everything mapped to "info" level.

Updated readme with the web link for haystack ollama integration

Let gpu.go and gen_linux.sh also find CUDA on Arch Linux

Refine the linux cuda/rocm developer docs

Add multiple CPU variants for Intel Mac