GitLab

* 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>

update embedded templates

chatglm graph

Wire up windows AMD driver reporting

Bundle missing CRT libraries

Detect CUDA OS overhead

Bump ROCm on windows to 6.1.2

Remove duplicate merge glitch

This also adjusts our algorithm to favor our bundled ROCm.
I've confirmed VRAM reporting still doesn't work properly so we
can't yet enable concurrency by default.

Workaround broken ROCm p2p copy

* stop token parsing fix

* add stop test

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.

Statically link c++ and thread lib on windows

This makes sure we statically link the c++ and thread library on windows
to avoid unnecessary runtime dependencies on non-standard DLLs

update named templates

update message processing

* server: fix unneeded model reloads when setting `OLLAMA_NUM_PARALLEL`

* remove whitespace change

* undo some changes

Some users are experienging runner startup errors due
to not having these msvc redist libraries on their host

Enable the build flag for llama.cpp to use CPU copy for multi-GPU scenarios.

llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535)

This reverts commit 5796bfc4.