When launching OpenClaw without prior onboarding, run the onboarding
wizard instead of going straight to gateway. This ensures proper
gateway configuration (mode, token, etc.) before first use.
- Add onboarded() to check for wizard.lastRunAt marker in config
- Run onboard with --auth-choice skip --gateway-token ollama for fresh installs
- Existing installs (onboarding completed) run gateway directly
- Fix panic in ollama show for image gen models (safe type assertion)
- Add vision capability for Flux2KleinPipeline models at create time
- Flatten transparent PNG images onto white background for better results
Move the unload check (empty prompt + KeepAlive=0) before the image
generation model dispatch in GenerateHandler. This prevents models like
flux from being loaded into memory just to be immediately unloaded when
running `ollama rm`.
Also fix a bug in DeleteHandler where `args[0]` was used instead of
`arg` in the delete loop, causing only the first model to be unloaded
when deleting multiple models.
* x: make `ollama create --experimental` import from safetensors
This change allows pulling in safetensors models into the new experimental model format, and also
fixes the `ollama show` command to be able to correctly display the model information.
* gofumpt the linter
* gofumpt the linter again
* validate the model name
TeaCache:
- Timestep embedding similarity caching for diffusion models
- Polynomial rescaling with configurable thresholds
- Reduces transformer forward passes by ~30-50%
FP8 quantization:
- Support for FP8 quantized models (8-bit weights with scales)
- QuantizedMatmul on Metal, Dequantize on CUDA
- Client-side quantization via ollama create --quantize fp8
Other bug fixes:
- Fix `/api/show` API for image generation models
- Server properly returns model info (architecture, parameters, quantization)
- Memory allocation optimizations
- CLI improvements for image generation
* cmd/bench: support writing benchmark output to file
This changes Ollama to allow the bench command to write benchmark
results to a user-specified output file instead of stdout when the
--output flag is provided.
---------
Co-authored-by: Patrick Devine <patrick@infrahq.com>
This change:
* fixes rope scaling in the mistral converter
* updates ministral to include llama4 scaling
* includes a new ministral parser for parsing reasoning and tool calling
---------
Co-authored-by: jmorganca <jmorganca@gmail.com>
This change adds a basic benchmarking test framework for Ollama which can
be used to determine the prefill, eval, load duration, and total duration
for running a given model or models.
Co-authored-by: A-Akhil <akhilrahul70@gmail.com>
This PR introduces a new ollama embed command that allows users to generate embeddings directly from the command line.
Added ollama embed MODEL [TEXT...] command for generating text embeddings
Supports both direct text arguments and stdin piping for scripted workflows
Outputs embeddings as JSON arrays (one per line)
this change fixes two bugs with `ollama rm`:
1. before a model is removed, it will first be stopped. this only
happens for the first argument and skipped for all other models
2. models are unloaded indiscriminately. this errors for cloud models
and should be omitted
There are two bugs when using `/load <model>` for a model that doesn't exist, namely:
1. it will not restore the current model settings if the current model is a thinking model; and
2. it will crash is the current model is a non-thinking model
This bug fix saves the current runOptions and then restores them if the model load
doesn't happen. It also fixes the crash happening for non-thinking models.
* auth: fix problems with the ollama keypairs
This change adds several fixes including:
- reading in the pubkey files correctly
- fixing the push unit test to create a keypair file in a temp directory
- not return 500 errors for normal status error
* bf16
* tests
* gpt-oss
* enable gptoss for engine
* rough estimate
* convert to mxfp4
* handle safetensors U8
* clamp glu/linear
* update tokenizer
* MXFP4 support
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.
* Unit tests for MXFP4 support
This exercises various operations and shapes on both CPU and GPU (if detected
on the system)
* cuda graph
* unit test adjustments
* cuda: optimize memory access
Read 4 bytes at a time (8 elements) when performing mul_mat_vec_mxfp4
* mac: fix crash on old macos versions
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.
* server: Minimum context length for gptoss
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.
* ggml: Multiply by numParallel for gptoss sliding window
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.
* gpt-oss integration
includes harmony parser and thinking levels, etc.
* fix sync
* fix tests
* fix lint
---------
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
Co-authored-by: Jesse Gross <jesse@ollama.com>
Co-authored-by: Devon Rifkin <drifkin@drifkin.net>
- Both `/api/generate` and `/api/chat` now accept a `"think"`
option that allows specifying whether thinking mode should be on or
not
- Templates get passed this new option so, e.g., qwen3's template can
put `/think` or `/no_think` in the system prompt depending on the
value of the setting
- Models' thinking support is inferred by inspecting model templates.
The prefix and suffix the parser uses to identify thinking support is
also automatically inferred from templates
- Thinking control & parsing is opt-in via the API to prevent breaking
existing API consumers. If the `"think"` option is not specified, the
behavior is unchanged from previous versions of ollama
- Add parsing for thinking blocks in both streaming/non-streaming mode
in both `/generate` and `/chat`
- Update the CLI to make use of these changes. Users can pass `--think`
or `--think=false` to control thinking, or during an interactive
session they can use the commands `/set think` or `/set nothink`
- A `--hidethinking` option has also been added to the CLI. This makes
it easy to use thinking in scripting scenarios like
`ollama run qwen3 --think --hidethinking "my question here"` where you
just want to see the answer but still want the benefits of thinking
models
* Move quantization logic to GGML via new backend
This moves the model aware logic to Go code and calls GGMLs quantization code for model creation.
* Remove "add model quantizations"
This is no longer needed now that quantization is implemented in Go+GGML code directly.
* increase default context length to 4096
We lower the default numParallel from 4 to 2 and use these "savings" to
double the default context length from 2048 to 4096.
We're memory neutral in cases when we previously would've used
numParallel == 4, but we add the following mitigation to handle some
cases where we would have previously fallen back to 1x2048 due to low
VRAM: we decide between 2048 and 4096 using a runtime check, choosing
2048 if we're on a one GPU system with total VRAM of <= 4 GB. We
purposefully don't check the available VRAM because we don't want the
context window size to change unexpectedly based on the available VRAM.
We plan on making the default even larger, but this is a relatively
low-risk change we can make to quickly double it.
* fix tests
add an explicit context length so they don't get truncated. The code
that converts -1 from being a signal for doing a runtime check isn't
running as part of these tests.
* tweak small gpu message
* clarify context length default
also make it actually show up in `ollama serve --help`
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.
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.
This fixes the case where a FROM line in previous modelfile points to a
file which may/may not be present in a different ollama instance. We
shouldn't be relying on the filename though and instead just check if
the FROM line was instead a valid model name and point to that instead.
Add metadata and tensor information to the show command to be able to
see more information about a model. This outputs the same data as
shown on the model details page on ollama.com
- output backend system info when initializing the backend. this ensures
this information is always present without needing to be called
explicitly
- convert to structured logging
- enumerate devices rather than backends since devices are ordered
- track device indices grouped by device name
* Include unified vision layers in memory prediction
For newer vision models with a single gguf, include
the projection estimates.
* Adjust CLI to handle both styles of vision model metadata
* Wire up new tokenizers for new engine
If we're loading the new engine, utilize the new model
text processor instead of calling into cgo wrappers for
llama.cpp. This also cleans up some tech debt from the
older tokenization flow for the C++ server which was
no longer used.
This also adjusts the grammar handling logic to pass
through to the new engine instead of utilizing the cgo
schema to grammar call.
* Lay foundation for auto selection of new engine
This provides integration with the new Ollama engine
(5824541 next ollama runner (#7913)) and the rest of the Ollama
infrastructure such as the runner and Ollama server.
In addition, it also builds out the KV cache infrastructure to
support requirements of how Ollama runs models such as:
- Parallel processing
- Memory management for defragmentation and shifting
- Multi-modal modals
Both old and new engines continue to be supported. By default, only
the old engine is used. To enable the new engine:
Start the server with the OLLAMA_NEW_ENGINE environment variable set:
OLLAMA_NEW_ENGINE=1 ./ollama serve
Start a model that is supported by the Ollama engine. This one is Llama 3.1 8b Q4_K_M:
./ollama run jessegross/llama3.1
* llama: wire up builtin runner
This adds a new entrypoint into the ollama CLI to run the cgo built runner.
On Mac arm64, this will have GPU support, but on all other platforms it will
be the lowest common denominator CPU build. After we fully transition
to the new Go runners more tech-debt can be removed and we can stop building
the "default" runner via make and rely on the builtin always.
* build: Make target improvements
Add a few new targets and help for building locally.
This also adjusts the runner lookup to favor local builds, then
runners relative to the executable, and finally payloads.
* Support customized CPU flags for runners
This implements a simplified custom CPU flags pattern for the runners.
When built without overrides, the runner name contains the vector flag
we check for (AVX) to ensure we don't try to run on unsupported systems
and crash. If the user builds a customized set, we omit the naming
scheme and don't check for compatibility. This avoids checking
requirements at runtime, so that logic has been removed as well. This
can be used to build GPU runners with no vector flags, or CPU/GPU
runners with additional flags (e.g. AVX512) enabled.
* Use relative paths
If the user checks out the repo in a path that contains spaces, make gets
really confused so use relative paths for everything in-repo to avoid breakage.
* Remove payloads from main binary
* install: clean up prior libraries
This removes support for v0.3.6 and older versions (before the tar bundle)
and ensures we clean up prior libraries before extracting the bundle(s).
Without this change, runners and dependent libraries could leak when we
update and lead to subtle runtime errors.
After a user pushes their model it is not clear what to do next. Add a link
to the output of `ollama push` that tells the user where their model can now
be found.
In the past the ollama.com server would return a JWT that contained
information about the user being authenticated. This was used to return
different error messages to the user. This is no longer possible since the
token used to authenticate does not contain information about the user
anymore. Removing this code that no longer works.
Follow up changes will improve the error messages returned here, but good to
clean up first.
This avoids emitting the progress indicators to stderr, and the interactive
prompts to the output file or pipe. Running "ollama run model > out.txt"
now exits immediately, and "echo hello | ollama run model > out.txt"
produces zero stderr output and a typical response in out.txt
Currently the CLI only sends images from the most recent image-
containing message. This prevents doing things like sending
one message with an image and then a follow message with a
second image and asking for comparision based on additional
information not present in any text that was output.
It's possible that some models have a problem with this but the
CLI is not the right place to do this since any adjustments are
model-specific and should affect all clients.
Both llava:34b and minicpm-v do reasonable things with multiple
images in the history.
Provide a mechanism for users to set aside an amount of VRAM on each GPU
to make room for other applications they want to start after Ollama, or workaround
memory prediction bugs
* Fix typo and improve readability
Summary:
* Rename updatAvailableMenuID to updateAvailableMenuID
* Replace unused cmd parameter with _ in RunServer function
* Fix typos in comments
(cherry picked from commit 5b8715f0b04773369e8eb1f9e6737995a0ab3ba7)
* Update api/client.go
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
---------
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
The OLLAMA_MAX_VRAM env var was a temporary workaround for OOM
scenarios. With Concurrency this was no longer wired up, and the simplistic
value doesn't map to multi-GPU setups. Users can still set `num_gpu`
to limit memory usage to avoid OOM if we get our predictions wrong.
This commit changes the 'ollama run' command to defer fetching model
information until it really needs it. That is, when in interactive mode.
It also removes one such case where the model information is fetch in
duplicate, just before calling generateInteractive and then again, first
thing, in generateInteractive.
This positively impacts the performance of the command:
; time ./before run llama3 'hi'
Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?
./before run llama3 'hi' 0.02s user 0.01s system 2% cpu 1.168 total
; time ./before run llama3 'hi'
Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?
./before run llama3 'hi' 0.02s user 0.01s system 2% cpu 1.220 total
; time ./before run llama3 'hi'
Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?
./before run llama3 'hi' 0.02s user 0.01s system 2% cpu 1.217 total
; time ./after run llama3 'hi'
Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?
./after run llama3 'hi' 0.02s user 0.01s system 4% cpu 0.652 total
; time ./after run llama3 'hi'
Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?
./after run llama3 'hi' 0.01s user 0.01s system 5% cpu 0.498 total
; time ./after run llama3 'hi'
Hi! It's nice to meet you. Is there something I can help you with or would you like to chat?
./after run llama3 'hi' 0.01s user 0.01s system 3% cpu 0.479 total
; time ./after run llama3 'hi'
Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?
./after run llama3 'hi' 0.02s user 0.01s system 5% cpu 0.507 total
; time ./after run llama3 'hi'
Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?
./after run llama3 'hi' 0.02s user 0.01s system 5% cpu 0.507 total
* API Show Extended
* Initial Draft of Information
Co-Authored-By: Patrick Devine <pdevine@sonic.net>
* Clean Up
* Descriptive arg error messages and other fixes
* Second Draft of Show with Projectors Included
* Remove Chat Template
* Touches
* Prevent wrapping from files
* Verbose functionality
* Docs
* Address Feedback
* Lint
* Resolve Conflicts
* Function Name
* Tests for api/show model info
* Show Test File
* Add Projector Test
* Clean routes
* Projector Check
* Move Show Test
* Touches
* Doc update
---------
Co-authored-by: Patrick Devine <pdevine@sonic.net>
* envconfig/config.go: Fix wrong description of OLLAMA_LLM_LIBRARY
Signed-off-by: Lei Jitang <leijitang@outlook.com>
* serve: Add more env to help message of ollama serve
Add more enviroment variables to `ollama serve --help`
to let users know what can be configurated.
Signed-off-by: Lei Jitang <leijitang@outlook.com>
---------
Signed-off-by: Lei Jitang <leijitang@outlook.com>
