GitLab

* Always filter devices

Avoid crashing on unsupported AMD iGPUs

* Remove cuda device filtering

This interferes with mixed setups

The recent memory management changes caused all GPUs to be visible
to the runner, regardless of whether they are ultimately used. This
caused CUDA devices to allocate a primary context (~300 MB VRAM) on
each GPU, for each model. This is unnecessary, so we can both avoid
touching GPUs that we exclude in the early stage of allocation and
freeing the memory for any that we touch but don't use.

The issue will continue to exist for the old engine, since it touches
all devices during initialization.

* convert: return bytes written

* ggml flavor mxfp4

* simplify jit conversion

* comment

there's two bugs here.

1. the check for a layer id is incorrect and should be >= 0 since layer
   0 is valid
2. if both tensors have an layer identifier, it will only compare the
   layer id which will return 0 if the tensors are in the same layer.
   instead it should fallback to comparing the full tensor name

thinking: fix double emit when no opening tag

Signed-off-by: zoupingshi <hangfachang@outlook.com>

The thinking parser will automatically transition to being a
pass-through if non-whitespace is seen before an opening tag. However,
we weren't clearing the buffer after the first non-whitespace input, so
in practice the first token would be emitted twice.

Added a test that demonstrated this, and then fixed the bug.

With old memory estimates, it's currently impossible to load more
than one model at a time when no GPUs are available. This is because
the check for whether we need to evict a model looks to see if all
layers of the new model can be loaded onto GPUs, which is never true
if there are no GPUs. Before the memory management changes, there
was a special code path for CPU-only systems.

This problem does not exist with new memory estimates.

Fixes #11974

model: fix boundary in bpe

0x007e is a tilde and was getting adjusted (+0x00a2) to 0x0120 in the
encode, but then in the decode it was getting adjusted down (-0x0100) to
0x0020. The boundary for the +0x00a2 case has been adjusted to fix this

Fixes: #11966

Flash attention kernels require the mask of the KV cache be a F16
rather than an F32. We can use the GGML operation ggml_cast to do
this rather than doing it ourselves, which allows reuse of a
preallocated buffer in the graph rather than allocating a new one
for each batch. This improves token generation performance with
flash attention by 10-30% (with gpt-oss). This also makes performance
with flash attention better than without it, as expected.

harmony: convert fn names to be valid ts identifiers

We dump out our best memory estimate after we complete processing
for any reason, including errors. This is helpful for finding what
what stopped us in error conditions but in some cases we might not
have gotten even the first result yet.

Fixes #11957

In <https://github.com/ollama/ollama/issues/11704#issuecomment-3177380197>
I noticed that hyphens in function names could possibly cause the model
to become confused. Later in that issue I found other explanations, but
at a minimum tool names with spaces in them are confusing to the model
because of the prompt format.

In this change I create a mapper that converts arbitrary tool names into
valid typescript identifiers. It's a little overly strict in that it
doesn't allow all unicode characters that might be valid in ts
identifiers, but it's still very permissive. Since mappings aren't
reversible, we must temporarily store this mapping in order to unmap it
if the model comes back with a call. We also handle the case where
multiple mappings collide into the same mapping and append a counter to
the end to make them unique

server: add debug option for printing out prompt instead of calling model

Docker build requires build-args to be defined.  This ensures the release.yaml settings will be used.

* test: improve scheduler/concurrency stress tests

The scheduler test used to use approximate memory figures and would often
over or under shoot a systems capcity leading to flaky test results.
This should improve the reliability of this scenario by leveraging
ps output to determinie exactly how many models it takes to
trigger thrashing.

The concurrency test is also refined to target num_parallel + 1 and handle
timeouts better.

With these refinements, TestMultiModelConcurrency was redundant

* test: add parallel generate with history

TestGenerateWithHistory will help verify caching and context
are properly handled while making requests

* test: focus embed tests on embedding models

remove non-embedding models from the embedding tests

This reverts commit dc5a6454.

This changes the memory allocation strategy from upfront estimation to
tracking actual allocations done by the engine and reacting to that. The
goal is avoid issues caused by both under-estimation (crashing) and
over-estimation (low performance due to under-utilized GPUs).

It is currently opt-in and can be enabled for models running on the
Ollama engine by setting OLLAMA_NEW_ESTIMATES=1. Behavior in other
cases is unchanged and will continue to use the existing estimates.