win: ensure ollama paths come first (ollama#10549)

For all search path env vars make sure our dirs are first
to avoid potentially finding other incompatible libraries
on the users system.

Also fixes a minor build script glitch for windows rocm

win: ensure ollama paths come first (ollama#10549)

For all search path env vars make sure our dirs are first
to avoid potentially finding other incompatible libraries
on the users system.

Also fixes a minor build script glitch for windows rocm

fix: write gguf padding (ollama#10510)

* add gguf_test

* fix padding

padding was being added to offset but not to the running count

strip out thinking tags in message history for qwen3 & r1 (ollama#10490)

* strip out thinking tags in message history for qwen3 & r1

This is in advance of "proper" support where we'll make reasoning
configurable and we'll parse out thinking/reasoning tags and provide
them to the caller. These models expect there to be no thinking tags in
the message history, so this should improve quality

* parse model names instead of hacky prefix check

integration: fix embedding tests error handling (ollama#10478)

The cleanup routine from InitServerconnection should run in the defer of the test case to properly detect failures and report the server logs

model: fix build (ollama#10416)

create tempdir in models directory

the models directory should have plenty of storage and also ensure
there's no cross-device copy

ml/backend/ggml: use default CUDA compression mode (ollama#10314)

ml: add missing cmake property and remove additional CMakeLists.txt (o…

…llama#10310)

Merge pull request ollama#10290 from ollama/drifkin/template-highligh…

…ting

docs: change more template blocks to have syntax highlighting