GitLab

the models directory should have plenty of storage and also ensure
there's no cross-device copy

Previously, the pull handler would send an error message in the Status
field, this prevented the client from using the message as a signal to
stop. In the case of the "run" command, it would follow the pull with a
"show" which would print a nearly identical "not found" message for
unresolved models.

Fixes #10307

docs: change more template blocks to have syntax highlighting

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

In #8215 syntax highlighting was added to most of the blocks, but there were a couple that were still being rendered as plaintext

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