GitLab

includes harmony parser and thinking levels, etc.

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.

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.

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.

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

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

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.

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