With support for multimodal models becoming more varied and common it is important for clients to be able to easily see what capabilities a model has. Retuning these from the show endpoint will allow clients to easily see what a model can do.
Clear KV cache when shift operation is not supported by model.
Added KvCacheCanShift() check to handle models that can't perform cache shifts,
falling back to full cache clear while preserving logical token history to
maintain expected behavior when context window fills up.
This change adds tracking of download chunks during the pull process so
that subsequent pulls can skip downloading already completed chunks.
This works across restarts of ollama.
Currently, download state will be lost if a prune is triggered during a
pull (e.g. restart or remove). This issue should be addressed in a
follow-up PR.
If we have an error after creating a new sequence but before
finding a slot for it, we return without releasing the semaphore.
This reduces our parallel sequences and eventually leads to deadlock.
In practice this should never happen because once we have acquired
the semaphore, we should always be able to find a slot. However, the
code is clearly not correct.
With the llama runner, we can generate up to NUM_PARALLEL batches
at once, which will then get broken up to into individual batches
to get executed by llama.cpp (i.e. we add up to 2048 tokens and
this gets split into 4 batches of 512 tokens at default settings).
This splitting can improve parallelism on multi-GPU systems because
the individual batches can move though the pipeline without blocking
on the first one to fully complete. However, we don't yet support
this in the Ollama runner, partially because it makes it hard to
enforce model-specified batch constraints, which didn't exist
previously.
The result is that we will try to execute the full, unsplit batch.
This could result in out of memory or insufficient KV cache space
errors.
This triggers batch breaking when the total inputs from all sequences
exceeds the batch size, rather than per-sequence. In order to ensure
fairness, it also reintroduces round-robinning around sequences so
that we don't let one busy sequence starve the others.
Model implementations should use Input for all of their tensors
supplied to the model. This includes tensors that relate to the
outputs, which is confusing since there is also an Output funciton.
Since Output is only used internally in GGML and not used by any
model implementations, we can remove it from the interface to
reduce confusion.
Gemma3 uses sliding windows for its context on 5/6 layers, significantly
reducing memory usage but leading to uneven usage across layers,
which makes allocation to the correct GPU difficult. We currently
estimate very conservatively by assuming all layers are consistent
at the max size.
Llama3.2-vision is also inconsistent between self attention and cross
attention layers - at moment, we calculate the correct total size
and then average this across layers. In some cases, this may lead
to crashes if a large layer is placed on a GPU sized by the average.
This allows memory estimation to calculate per-layer KV cache size
and take this account when placing layers onto GPUs. We already do
this for weights that vary per-tensor, so this is a logical extension.
Fixes#9730Fixes#9890
When computing the size of the cache for sliding window attention,
we don't need to multiple the batch size by the number of parallel
sequences - the batch size is constant.
This also simplifies the check for whether to allocate the cache
size based on capacity or window size as the batch size is already
incorporated into the capacity when handled by the runner.
Close chunked writers as soon as downloads complete, rather than
deferring closure until Pull exits. This prevents exhausting file
descriptors when pulling many layers.
Instead of unbounded defers, use a WaitGroup and background goroutine
to close each chunked writer as soon as its downloads finish.
Also rename 'total' to 'received' for clarity.
Currently sliding window attention allocates and uses the full
context size and just masks out any tokens that are outside of the
window. However, we really only need (roughly) the sliding window
size.
At large context sizes this improves two things:
- Memory allocated - since the fully context size is allocated up front,
memory requirements drop substantially. On Gemma3:4b with a 32k
context window, total memory usage (including weights and non-sliding
layers) drops from ~20GB to ~8GB.
- Computation - ranges that are completely outside of the sliding
window are now removed from the tensors that are returned from the
cache rather than simply being masked out. This results in more
efficient processing, scaling with the size of the context that
has actually been used.
Notable, this does not update the scheduler for any model to be aware of
the smaller memory requirements. This is difficult for Gemma3 because
the layers are heterogeneous between sliding and non-sliding attention.
As a result, while actual memory consumption will be reduced, the
scheduler will over-estimate the requirements of the model. This means
that splitting between GPUs or GPUs and CPUs will still be suboptimal.
Bug #9730
Currently the runner computes the kv size needed and creates a
cache of that size. This is the context size times number of
parallel sequences.
Cache implementations can make better decisions about their memory
usage, so instead pass in the required capacity, number of sequences
and maximum batch size. For now, the causal cache just uses this to
compute the size in the same way as before.
This enables the runner to report progress back to the Ollama server,
both for showing status to the user and also to prevent the server
from killing the runner if it thinks things have stalled.
Most of the infrastructure was already there, this extends it to
be available to the backends.
Defragging the KV cache can generate a lot of operations, so we
need to be careful that we don't overflow the number that the graph
can support. We currently account for all of the nodes that we add
to the graph for each move but we also need to include the original
cache tensors as well.
Fixes#9904
Rather than directly giving the input data to models, we can
pass a tensor instead. In the short term, this saves some duplicated
code.
Longer term, we will want to overlap setting up the next batch with
processing of the current one. In this case, we will only have the
shape of tensor but it will not be loaded with data at the time of
graph generation. By passing only a tensor to models now, we set up
this possibility and prevent them from relying on data that they won't
have in the future.
Although the same could be done for Positions and Outputs, in some
cases we either need the raw input data or don't use them at all.
Therefore, for now we leave them as they are and allow models to
convert them to tensors as needed.
If the chunksums response is missing a chunk, the client should fail
the download. This changes the client to check that all bytes are
accounted for in the chunksums response.
It is possible there are overlaps or gaps in the chunksums response and
so the size is not the only thing left to check, but this provides
enough coverage for now. We may want to check that chunks are contiguous
later.
When converting a ggml model if there is a failure to read tensor data a nil error value was being returned. It should be assigned to the actual error from reading.
Models can specify that a group of inputs need to be handled a single
batch. However, context shifting didn't respect this and could trigger
a break anyways. In this case, we should instead trigger a context
shift earlier so that it occurs before the grouped batch.
Note that there still some corner cases:
- A long prompt that exceeds the context window can get truncated
in the middle of an image. With the current models, this will
result in the model not recognizing the image at all, which is
pretty much the expected result with truncation.
- The context window is set less than the minimum batch size. The
only solution to this is to refuse to load the model with these
settings. However, this can never occur with current models and
default settings.
Since users are unlikely to run into these scenarios, fixing them is
left as a follow up.
We do not need to bypass the prompt caching in the ollama runner yet, as
only embedding models needed to bypass the prompt caching. When embedding
models are implemented they can skip initializing this cache completely.
Bruce MacDonald
IsAurora6
Ilian
Abyss-c0re
湛露先生
Blake Mizerany
Jesse Gross
Leandro Borges Ferreira
CYJiang
saman-amd
Parth Sareen
molbal
Hengky Steen
copeland3300
Matheus C. França
Michael Yang
Patrick Devine
rylativity
Jeffrey Morgan