GitLab

* 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

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

* Adjust initial scheduler refCount

Ensure we only set the refCount on success

* sched: fix lock order inversion deadlock

Under certain race conditions, there was a scenario where the scheduler would
get into a deadlock while trying to update free space information while a model
was trying to unload.

Users may have other incompatible GGML installs on their systems.
This will prevent us from trying to load them from the path.

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

When we later have a large batch running purely on a CPU, this
results the error:
GGML_ASSERT(talloc->buffer_id >= 0)

Disabling this means that we will incrementally reallocate memory
as the graph grows.

Fixes #10410

this is in part to "pay" for #10452, which doubled the default context length. The combination isn't fully neutral though, because even though the old 4x2k limit and the new 2x4k limit are memory equivalent, the 1x fallback is larger with 4k

config: update default context length to 4096

Revert "increase default context length to 4096"

This reverts commit 424f6486.

Co-authored-by: Patrick Devine <patrick@infrahq.com>

use a default of 1024 when asking for zero is confusing since most calls
seem to assume 0 means do not ready any data

the first call to http.ResponseWriter.Write implicitly calls WriteHeader
with http.StatusOK if it hasn't already been called. once WriteHeader
has been called, subsequent calls has no effect. Write is called when
JSON encoding progressUpdateJSON{}. calls to
http.ResponseWriter.WriteHeader after the first encode is useless and
produces a warning:

http: superfluous response.WriteHeader call from github.com/ollama/ollama/server/internal/registry.(*statusCodeRecorder).WriteHeader (server.go:77)

* increase default context length to 4096

We lower the default numParallel from 4 to 2 and use these "savings" to
double the default context length from 2048 to 4096.

We're memory neutral in cases when we previously would've used
numParallel == 4, but we add the following mitigation to handle some
cases where we would have previously fallen back to 1x2048 due to low
VRAM: we decide between 2048 and 4096 using a runtime check, choosing
2048 if we're on a one GPU system with total VRAM of <= 4 GB. We
purposefully don't check the available VRAM because we don't want the
context window size to change unexpectedly based on the available VRAM.

We plan on making the default even larger, but this is a relatively
low-risk change we can make to quickly double it.

* fix tests

add an explicit context length so they don't get truncated. The code
that converts -1 from being a signal for doing a runtime check isn't
running as part of these tests.

* tweak small gpu message

* clarify context length default

also make it actually show up in `ollama serve --help`