with #12181, there's now support for embeddings in ollama engine.
this is done by mutating the architecture and adding _embed when it
detects an embedding model. however this introduced a bug where if
an embedding model was run based on an existing ollama engine model
without an embedding implementation, e.g. llama4, it will pass the
initial arch support check but fail when actually loaded.
there's currently two entrypoints to creating a model. previously this
second entrypoint was necessary because calling model.New would also
load the model. since #11818, this is no longer th case so merge them
to reduce complexity
With the addition of cuda v13, on a clean setup, the level of parallelism
was causing docker desktop to become overwhelmed and compilers
were crashing. This limits to 8 parallel per build stage, with the ability
to override if you have many more cores available.
This change moves back to converting bf16 vision weights to fp16,
specifically if they start with the name "v." (such as v.blk.0.attn_k.weight).
This fixes a bug where converted images are failing because they are trying
to call `im2col` which doesn't have a bf16 kernel in ggml.
The format qwen3-coder uses is relatively unique, both in rendering and
in parsing. To implement parsing, I wrote a custom parser in similar
style to harmony. For the rendering, I found that the logic would be
much more difficult to follow in a template, so I introduced the concept
of a built-in renderer that uses go code, rather than a template to
generate prompts.
I set us up for future built-in parsers and renderers by making it so
they can be specified in a Modelfile like so:
```
RENDERER "qwen3-coder"
PARSER "qwen3-coder"
```
These need to be provided explicitly because the architecture alone is
not enough to understand what format the model expects to receive, and
what format we expect it to output (e.g., qwen3-coder is `qwen3moe`,
which includes other qwen3-family models as well)
I haven't converted harmony to be one of these "built-ins" yet, since
some of it is in flux with the changes @ParthSareen has been making to
move harmony to the runner. It is likely that many other built-ins will
need to move to the runner as well, but I'm able to slightly defer that
decision since qwen3-coder doesn't have thinking (and therefore doesn't
need to be in the runner to make structured outputs work). I expect to
unify harmony with this approach very soon.
Whether a particular model supports tools or thinking was previously
inferred from templates, but without a template we now also use the
parser itself to declare what it supports. If we have future models that
re-use the same parsing format, but have different capabilities, we'll
want to parameterize them and give them different names to be specified
as a `PARSER`.
Misc changes:
- I worked on the renderer by diffing outputs from the reference
implementation and ours. To make it easier to do this, I extended
<https://github.com/ollama/ollama/pull/11875> to also support
returning the prompt via the openai compat layer
Ollama's recent engine update, llama.cpp, caused all models requiring a slice schema to not display images. As a result, the value of numTokens isn't always the length of the sliced image embed, but rather the end length of the schema. This causes the image embed to not be correctly included during all slice processing.
If a model with a split vision projector is loaded in the Ollama
engine, the projector will be ignored and the model will hallucinate
a response. Instead, fallback and try to load the model in the llama
engine.
New memory estimates (see #11090 for more information) are now
enabled automatically for all models running on the Ollama engine,
improving both stability and performance through more accurate sizing
and allocation. Models running on the llama engine will continue to
use the original style of memory estimation.
Our new engine implementation of gemma2 doesn't support flash
attention, which means that it also doesn't support KV cache
quantization. Currently, it is possible to turn these two on,
which will result in a crash.
If flash attention is enabled without KV cache quanitization, we will
currently always get this warning:
level=WARN source=server.go:226 msg="kv cache type not supported by model" type=""
* Add support for upcoming NVIDIA Jetsons
The latest Jetsons with JetPack 7 are moving to an SBSA compatible model and
will not require building a JetPack specific variant.
* cuda: bring back dual versions
This adds back dual CUDA versions for our releases,
with v11 and v13 to cover a broad set of GPUs and
driver versions.
* win: break up native builds in build_windows.ps1
* v11 build working on windows and linux
* switch to cuda v12.8 not JIT
* Set CUDA compression to size
* enhance manual install linux docs
* tests: reduce stress on CPU to 2 models
This should avoid flakes due to systems getting overloaded with 3 (or more) models running concurrently
* tests: allow slow systems to pass on timeout
If a slow system is still streaming a response, and the response
will pass validation, don't fail just because the system is slow.
* test: unload embedding models more quickly
The context must always be able to store the current batch, so
if the user requests a small context then we should also shrink
the batch to match. This also fixes the TestLongInputContext
test on the new engine. (The old engine already has this behavior.)
This PR updates the memory size estimate logic to better handle recurrent and hybrid-recurrent models which are currently being badly overestimated because the default logic assumes full attention for all layers.
The logic for the sizing of the recurrent layers comes from the llama.cpp implementation
ggml_tensor * r = ggml_new_tensor_1d(ctx, type_r, hparams.n_embd_r()*mem_size);
ggml_tensor * s = ggml_new_tensor_1d(ctx, type_s, hparams.n_embd_s()*mem_size);
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
