GitLab

* dont clamp ctx size in `PredictServerFit`

* minimum 4 context

* remove context warning

This records more GPU usage information for eventual UX inclusion.

This will bubble up a much more informative error message if noexec
is preventing us from running the subprocess

Trying to live off the land for cuda libraries was not the right strategy.  We need to use the version we compiled against to ensure things work properly

* fix llava models not working after first request

* individual requests only for llava models

This moves all the env var reading into one central module
and logs the loaded config once at startup which should
help in troubleshooting user server logs

log when the waiting for the process to stop to help debug when other tasks execute during this wait.
expire timer clear the timer reference because it will not be reused.
close will clean up expireTimer if calling code has not already done this.

* llm: limit generation to 10x context size to avoid run on generations

* add comment

* simplify condition statement

Tmp cleaners can nuke the file out from underneath us.  This detects the missing
runner, and re-initializes the payloads.

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.

* terminate subprocess if receiving `SIGINT` or `SIGTERM` signals while model is loading

* use `unload` in signal handler

During testing, we're seeing some models take over 3 minutes.

This should resolve a number of memory leak and stability defects by allowing
us to isolate llama.cpp in a separate process and shutdown when idle, and
gracefully restart if it has problems.  This also serves as a first step to be
able to run multiple copies to support multiple models concurrently.