GitLab

This removes the extra flushProgress() at the end of handlePull. It is
unnecessary because final progress updates are flushed in all cases of
the main select loop.

The completed and received counters must work in tandem and the code
should better reflect that. Previously, the act of updating them was 2-3
lines of code duplicated in multiple places. This consolidates them into
a single update closure for easy reading and maintenance.

This also simplifies error handling in places where we can use a return
parameter and defer to handle the error case for updates.

Also, remove the old Layer field from the trackingReader struct.

Add some new test coverage for various model architectures,
and switch from orca-mini to the small llama model.

Fix flake failures on windows

This commit adds retry/backoff to the registry client for pull requests.

Also, revert progress indication to match original client's until we can
"get it right."

Also, make WithTrace wrap existing traces instead of clobbering them.
This allows clients to compose traces.

When ggml_backend_buffer_free() is called, the device memory
is released but not all backends consistently release the actual
ggml_backend_buffer_t in system RAM, causing a memory leak.

Bug #10040

server: add `OpenAI-Beta` header to CORS safelist

docs: update some response code blocks to json5

This is to prevent rendering bright red comments indicating invalid JSON when the comments are just supposed to be explanatory

alphabetized the compat list and then added a single header

fixes: #9801

For every forward pass through the model, we need to allocate input
tensors: tokens, images, positions, outputs and masks. These get
allocated in system memory.

However, when we close the context that the tensors were allocated
through, the metadata gets freed but the actual backend memory does
not. This results in a significant memory leak.

This makes it so that all the memory allocated through a context
gets freed when it is closed.

Fixes #10040

Allocating (and in particular, freeing) memory from CUDA host buffers
is expensive and can cause a significant performance hit if we do
it for every token. Using normal system memory avoids this issue
and also gives the OS more flexibility to manage it.

There is no performance impact from this patch directly (either
positive or negative) but it makes a difference once we start
freeing memory correctly.

Context is currently mixed between pointer and value receivers. Change
this to be all pointer receivers so don't have to reason about whether
the things we are updating in the struct will be retained.

Sometimes loading the GGUF file fails with:
panic: context canceled

This is probably a filesystem error but it doesn't provide any
information about what happened.

---------
Co-authored-by: Parth Sareen <parth.sareen@ollama.com>

Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>

Signed-off-by: googs1025 <googs1025@gmail.com>

* cleanup: remove OLLAMA_TMPDIR
* cleanup: ollama doesn't use temporary executables anymore

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

Currently, the KV cache and graph are lazily allocated as needed.
The cache is fully allocated on first use of the corresponding
layer whereas the graph grows with the size of the context.

This can be an issue if another application allocates more VRAM
after we do our calculations - Ollama will crash in the middle of
inference. If we instead allocate the maximum needed memory at
startup of the runner, we will either succeed or fail at that point
rather than at some surprising time in the future.

Currently, this only generates a worst case batch for text, which
means that vision models may get a partial allocation and continue
to lazily allocate the rest.

If there is a CUDA OOM, we currently don't check the return value
and will evetually segfault. This checks for the problem and generates
a Go error. At the moment, this will still result in a panic but having
the error is the first step to being able to handle it more gracefully.

CONTRIBUTING: fix code block formatting

There were only 3 spaces instead of 4, so the example was being considered to include html elements

improves model loading times on network-based filesystems
such as GCS fuse by creating a dedicated file descriptor for each
section of the file being read, reducing seeking

Mistral is a popular research lab making open source models. This updates
the forward pass of llama architecture models to support both llama models
and mistral models by accounting for additional metadata present in mistral
models, and finding the correct dimensions for the output projection.

fs: move ml.Config to fs package

No functional change. Many different done reasons can be set at the runner
level, so rather than obsuring them we should return them to the server
process and let it choose what to do with the done reason. This separates
the API concerns from the runner.

The sliding window cache trims entries that are outside the window for
the latest token. This works when we are extending the cache, such as
when the conversation continues. However, if we have a partial overlap
in conversation (including the BOS tokens), then we resume from a past
point in the conversation and the needed tokens are no longer stored
in memory. This verifies that the new window overlaps with the old one
before reusing the cache.
Co-authored-by: Jesse Gross <jesse@ollama.com>

When truncating inputs to the the context window at the beginning of
a sequence, we remove the minimum amount possible. However, this
may cause us to truncate to the middle of a set of inputs that
the model specified should not be split up. To avoid this, we
need to remove the rest of the partial batch.