GitLab

* llama: wire up builtin runner

This adds a new entrypoint into the ollama CLI to run the cgo built runner.
On Mac arm64, this will have GPU support, but on all other platforms it will
be the lowest common denominator CPU build.  After we fully transition
to the new Go runners more tech-debt can be removed and we can stop building
the "default" runner via make and rely on the builtin always.

* build: Make target improvements

Add a few new targets and help for building locally.
This also adjusts the runner lookup to favor local builds, then
runners relative to the executable, and finally payloads.

* Support customized CPU flags for runners

This implements a simplified custom CPU flags pattern for the runners.
When built without overrides, the runner name contains the vector flag
we check for (AVX) to ensure we don't try to run on unsupported systems
and crash.  If the user builds a customized set, we omit the naming
scheme and don't check for compatibility.  This avoids checking
requirements at runtime, so that logic has been removed as well.  This
can be used to build GPU runners with no vector flags, or CPU/GPU
runners with additional flags (e.g. AVX512) enabled.

* Use relative paths

If the user checks out the repo in a path that contains spaces, make gets
really confused so use relative paths for everything in-repo to avoid breakage.

* Remove payloads from main binary

* install: clean up prior libraries

This removes support for v0.3.6 and older versions (before the tar bundle)
and ensures we clean up prior libraries before extracting the bundle(s).
Without this change, runners and dependent libraries could leak when we
update and lead to subtle runtime errors.

This adds support for the Jetson JetPack variants into the Go runner

Until we have full NUMA support, this adjusts the default thread selection
algorithm to count up the number of performance cores across all sockets.

Cleaning up go package naming

On windows, detect large multi-socket systems and reduce to the number of cores
in one socket for best performance

* Expose GPU discovery failure information

* Remove exposed API for now

The recent cuda variant changes uncovered a bug in ByLibrary
which failed to group by common variant for GPU types.

Based on compute capability and driver version, pick
v12 or v11 cuda variants.

This adds new variants for arm64 specific to Jetson platforms

* llm: avoid loading model if system memory is too small

* update log

* Instrument swap free space

On linux and windows, expose how much swap space is available
so we can take that into consideration when scheduling models

* use `systemSwapFreeMemory` in check

---------
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>

This adds logic to detect skew between the driver and
management library which can be attributed to OS overhead
and records that so we can adjust subsequent management
library free VRAM updates and avoid OOM scenarios.

Until ROCm v6.2 ships, we wont be able to get accurate free memory
reporting on windows, which makes automatic concurrency too risky.
Users can still opt-in but will need to pay attention to model sizes otherwise they may thrash/page VRAM or cause OOM crashes.
All other platforms and GPUs have accurate VRAM reporting wired
up now, so we can turn on concurrency by default.

Implement support for GPU env var workarounds, and leverage
this for the Vega RX 56 which needs
HSA_ENABLE_SDMA=0 set to work properly

Still not complete, needs some refinement to our prediction to understand the
discrete GPUs available space so we can see how many layers fit in each one
since we can't split one layer across multiple GPUs we can't treat free space
as one logical block

Now that we call the GPU discovery routines many times to
update memory, this splits initial discovery from free memory
updating.

This cleans up the logging for GPU discovery a bit, and can
serve as a foundation to report GPU information in a future UX.

This change adds support for multiple concurrent requests, as well as
loading multiple models by spawning multiple runners. The default
settings are currently set at 1 concurrent request per model and only 1
loaded model at a time, but these can be adjusted by setting
OLLAMA_NUM_PARALLEL and OLLAMA_MAX_LOADED_MODELS.

count each layer independently when deciding gpu offloading

This wires up some new logic to start using sysfs to discover AMD GPU
information and detects old cards we can't yet support so we can fallback to CPU mode.

In some cases we may want multiple variants for a given GPU type or CPU.
This adds logic to have an optional Variant which we can use to select
an optimal library, but also allows us to try multiple variants in case
some fail to load.

This can be useful for scenarios such as ROCm v5 vs v6 incompatibility
or potentially CPU features.

This refines the gpu package error handling and fixes a bug with the
system memory lookup on windows.

Refactor where we store build outputs, and support a fully dynamic loading
model on windows so the base executable has no special dependencies thus
doesn't require a special PATH.

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.