GitLab

KV cache quantization has a dependency on the flash attention kernel.
We currently cannot use flash attention with gpt-oss as it requires
additional operations.

The model definition does not call flash attention, so it works
regardless of the setting but the cache will pick up the
quantization type. This updates the flash attention setting earlier
in the loading flow so that all downstream settings are also set correctly.

Fixes: #11671

* bf16

* tests

* gpt-oss

* enable gptoss for engine

* rough estimate

* convert to mxfp4

* handle safetensors U8

* clamp glu/linear

* update tokenizer

* MXFP4 support

This implements the Open Compute Microscaling (MX) FP4 format
as a tensor type with backend implementations focusing
on mulmat and mulmatid on CPU, CUDA, and Metal.

* Unit tests for MXFP4 support

This exercises various operations and shapes on both CPU and GPU (if detected
on the system)

* cuda graph

* unit test adjustments

* cuda: optimize memory access

Read 4 bytes at a time (8 elements) when performing mul_mat_vec_mxfp4

* mac: fix crash on old macos versions

cblas_sgemm is only supported on v13.3 and up, however bf16 is
only supported on v14+ so we were falling back to ggml-blas and
crashing on bf16 tensors.  Checking for the function being null
seems to be the simplest way to condittionally avoid registering the
backend.

* server: Minimum context length for gptoss

This model requires a minimum context length of 8192 to function
effectively. Users can set higher values through all normal mechanisms
but lower values will be silently reset.

* ggml: Multiply by numParallel for gptoss sliding window

When computing the graph size estimate, the context size is already
multiplied by numParallel so estimates reflect that. However, since
sliding window models use a smaller, fixed context size, they need
to manually take numParallel into account.

* gpt-oss integration

includes harmony parser and thinking levels, etc.

* fix sync

* fix tests

* fix lint

---------
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
Co-authored-by: Jesse Gross <jesse@ollama.com>
Co-authored-by: Devon Rifkin <drifkin@drifkin.net>

There is a bug when using sliding window attention where we run
out of KV cache slots. This is likely due to not correctly removing
all of the entries as they slide out of range. This adds additional
logging when this occurs to track down the source.

Bug #10127

Models that use sliding window attention can only resume a sequence
from the cache if it falls within the saved windows. This works well
if the next message picks up where the old one left off. However, it
generally prevents a partial prefix match unless the entire conversation
falls within the sliding window.

This can be a problem with reasoning models where the traces are
supposed to be removed from future messages, forcing the entire
history to be re-evaluated.

This change allows models to specify that a larger amount of the
history be retained in memory, to allow more partial resumption.
It still respects the window that the model was trained on for
token generation.

This reverts commit 9d071e6089319b37acf62bb739e3430dcb2ac0c3.

Support for bf16 was added in MacOS v14+ and attempting to enable
on older versions causes runtime failures.

* Enable CUDA Graphs for gemma3n.

Similar to
https://github.com/ggml-org/llama.cpp/pull/14741,
though ollama has a slightly different model graph
than llama.cpp which requires different workaround
checks.

* Remove residual check by reshaping differently in gemma3n model

This should make the heuristics more robust

When we context shift, we delete half the context and apply RoPE
with an offset to the other half. We used to RoPE across the entire
context in a single pass with a zero offset for the deleted
section. With the change to shifting in batches, we can skip any
batches where all of the offsets would be zero. This typically
reduces the number of operations by half.

Currently, when we need to do a shift on the cache, it is one
RoPE operation on the entire size of the cache (per layer). In
some cases, this can create a compute graph that is larger than
the forward pass since the forward pass is working in batches.
Since we don't consider shifting in our memory estimates, it's
possible for this to cause a crash if we run out of memory.

By limiting the size of the RoPE calls to batch size chunks, we
ensure that the shift will never exceed the size of the forward
pass, since the forward pass will also contain a RoPE of the same
size. This does not have a sigificant impact on performance since
RoPE is a math operation that is mostly proportional to the size
of its inputs.

In theory defrag could have the same issue since it also creates a
compute graph outside of the forward pass, however, since it is
only copies, it does not require any working space.

---------
Co-authored-by: Richard Lyons <frob@cloudstaff.com>

Co-authored-by: frob <rick+github@frob.com.au>

The macos-13 is x86, while macos-13-xlarge is arm64

Co-authored-by: Richard Lyons <frob@cloudstaff.com>

StatusError was unreachable, the client always checked for error messages in the response body first, and the server always includes error messages with HTTP error status codes.

As in the commit 44b466ee, the default context length has been increased to 4096.

Reporting params.NumGPULayers can be misleading because it is the
requested number of layers, not the actual number that is loaded.
While they are often the same, there are cases where they might mismatch,
such as if the GPU backend is missing.

We're not currently using it, even in cases where we could. Disabling
it improves generation performance by 10-30% with multiple GPUs.

* Only load supported models on new engine

Verify the model is supported before trying to load

* int: testcase for all library models

We don't get valid UUIDs for AMD GPUs on Windows, so the best option
is to use the ordinal IDs. This brings us in line with what we currently
do on the Ollama server - the only exception is AMD GPUs on Linux, which
falls back to using ordinal IDs. The GGML implementation has no fallback
but it doesn't appear to occur for any of the GPUs that we support.

It's also possible that there are collisions between ordinal IDs for
different libraries - however the only places where we use them are
AMD on Windows and Metal on Mac, which can never occur on the same
system.

also removes stale model dir instructions for windows

The current scheduler algorithm of picking the paralellism based on available
VRAM complicates the upcoming dynamic layer memory allocation algorithm.  This
changes the default to 1, with the intent going forward that parallelism is
explicit and will no longer be dynamically determined.  Removal of the dynamic
logic will come in a follow up.

* API: expose context size of loaded models

* CLI: add context UX

This adds a column in the ps output to show the models context size.