This change allows for mixed-case model names to be pushed, pulled,
copied, and created, which was previously disallowed because the Ollama
registry was backed by a Docker registry that enforced a naming
convention that disallowed mixed-case names, which is no longer the
case.
This does not break existing, intended, behaviors.
Also, make TestCase test a story of creating, updating, pulling, and
copying a model with case variations, ensuring the model's manifest is
updated correctly, and not duplicated across different files with
different case variations.
The Go runner does not have a problem with supporting parallel
requests for most multimodal models. Now that we won't be potentially
falling back to server.cpp, this restriction can be lifted.
However, the new mllama model can't support parallel requests, so we
will need to keep a restriction for that.
One potential failure mode is an empty file which bubbles up as an EOF error,
leading to all pulls and listing operations failing. Instead, continue and
warn about the corrupt manifest. This also allows re-pulling the corrupt
manifest to repair the system.
Currently we assume that images take 768 tokens of context size for
the purposes of clipping old messages that exceed the context window.
However, our mllama implementation stores the full image embedding
in a single token. As a result, there is significant waste of context
space.
Ideally, we would handle this more generically and have the
implementation report the number of tokens. However, at the moment
this would just result in a similar set of 'if' conditions in the
runner plus APIs to report it back. So for now, we just keep this
simple.
-Update mllama to take the cross attention state as embeddings in
a batch, more similar to how Llava handles it. This improves
integration with the input cache.
-Pass locations in a prompt for embeddings using tags similar to Llava.
-Abstract interface to vision models so the main runner accesses Clip
and Mllama similarly
Co-authored-by: Michael Yang <mxyng@pm.me>
* Re-introduce the llama package
This PR brings back the llama package, making it possible to call llama.cpp and
ggml APIs from Go directly via CGo. This has a few advantages:
- C APIs can be called directly from Go without needing to use the previous
"server" REST API
- On macOS and for CPU builds on Linux and Windows, Ollama can be built without
a go generate ./... step, making it easy to get up and running to hack on
parts of Ollama that don't require fast inference
- Faster build times for AVX,AVX2,CUDA and ROCM (a full build of all runners
takes <5 min on a fast CPU)
- No git submodule making it easier to clone and build from source
This is a big PR, but much of it is vendor code except for:
- llama.go CGo bindings
- example/: a simple example of running inference
- runner/: a subprocess server designed to replace the llm/ext_server package
- Makefile an as minimal as possible Makefile to build the runner package for
different targets (cpu, avx, avx2, cuda, rocm)
Co-authored-by: Jesse Gross <jesse@ollama.com>
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
* cache: Clear old KV cache entries when evicting a slot
When forking a cache entry, if no empty slots are available we
evict the least recently used one and copy over the KV entries
from the closest match. However, this copy does not overwrite
existing values but only adds new ones. Therefore, we need to
clear the old slot first.
This change fixes two issues:
- The KV cache fills up and runs out of space even though we think
we are managing it correctly
- Performance gets worse over time as we use new cache entries that
are not hot in the processor caches
* doc: explain golang objc linker warning (#6830)
* llama: gather transitive dependencies for rocm for dist packaging (#6848)
* Refine go server makefiles to be more DRY (#6924)
This breaks up the monolithic Makefile for the Go based runners into a
set of utility files as well as recursive Makefiles for the runners.
Files starting with the name "Makefile" are buildable, while files that
end with ".make" are utilities to include in other Makefiles. This
reduces the amount of nearly identical targets and helps set a pattern
for future community contributions for new GPU runner architectures.
When we are ready to switch over to the Go runners, these files should
move to the top of the repo, and we should add targets for the main CLI,
as well as a helper "install" (put all the built binaries on the local
system in a runnable state) and "dist" target (generate the various
tar/zip files for distribution) for local developer use.
* llama: don't create extraneous directories (#6988)
* llama: Exercise the new build in CI (#6989)
Wire up some basic sanity testing in CI for the Go runner. GPU runners are not covered yet.
* llama: Refine developer docs for Go server (#6842)
This enhances the documentation for development focusing on the new Go
server. After we complete the transition further doc refinements
can remove the "transition" discussion.
* runner.go: Allocate batches for all sequences during init
We should tell the model that we could have full batches for all
sequences. We already do this when we allocate the batches but it was
missed during initialization.
* llama.go: Don't return nil from Tokenize on zero length input
Potentially receiving nil in a non-error condition is surprising to
most callers - it's better to return an empty slice.
* runner.go: Remove stop tokens from cache
If the last token is EOG then we don't return this and it isn't
present in the cache (because it was never submitted to Decode).
This works well for extending the cache entry with a new sequence.
However, for multi-token stop sequences, we won't return any of the
tokens but all but the last one will be in the cache. This means
when the conversation continues the cache will contain tokens that
don't overlap with the new prompt.
This works (we will pick up the portion where there is overlap) but
it causes unnecessary cache thrashing because we will fork the original
cache entry as it is not a perfect match.
By trimming the cache to the tokens that we actually return this
issue can be avoided.
* runner.go: Simplify flushing of pending tokens
* runner.go: Update TODOs
* runner.go: Don't panic when processing sequences
If there is an error processing a sequence, we should return a
clean HTTP error back to Ollama rather than panicing. This will
make us more resilient to transient failures.
Panics can still occur during startup as there is no way to serve
requests if that fails.
Co-authored-by: jmorganca <jmorganca@gmail.com>
* runner.go: More accurately capture timings
Currently prompt processing time doesn't capture the that it takes
to tokenize the input, only decoding time. We should capture the
full process to more accurately reflect reality. This is especially
true once we start processing images where the initial processing
can take significant time. This is also more consistent with the
existing C++ runner.
* runner.go: Support for vision models
In addition to bringing feature parity with the C++ runner, this also
incorporates several improvements:
- Cache prompting works with images, avoiding the need to re-decode
embeddings for every message in a conversation
- Parallelism is supported, avoiding the need to restrict to one
sequence at a time. (Though for now Ollama will not schedule
them while we might need to fall back to the old runner.)
Co-authored-by: jmorganca <jmorganca@gmail.com>
* runner.go: Move Unicode checking code and add tests
* runner.go: Export external cache members
Runner and cache are in the same package so the change doesn't
affect anything but it is more internally consistent.
* runner.go: Image embedding cache
Generating embeddings from images can take significant time (on
my machine between 100ms and 8s depending on the model). Although
we already cache the result of decoding these images, the embeddings
need to be regenerated every time. This is not necessary if we get
the same image over and over again, for example, during a conversation.
This currently uses a very small cache with a very simple algorithm
but it is easy to improve as is warranted.
* llama: catch up on patches
Carry forward solar-pro and cli-unicode patches
* runner.go: Don't re-allocate memory for every batch
We can reuse memory allocated from batch to batch since batch
size is fixed. This both saves the cost of reallocation as well
keeps the cache lines hot.
This results in a roughly 1% performance improvement for token
generation with Nvidia GPUs on Linux.
* runner.go: Default to classic input cache policy
The input cache as part of the go runner implemented a cache
policy that aims to maximize hit rate in both single and multi-
user scenarios. When there is a cache hit, the response is
very fast.
However, performance is actually slower when there is an input
cache miss due to worse GPU VRAM locality. This means that
performance is generally better overall for multi-user scenarios
(better input cache hit rate, locality was relatively poor already).
But worse for single users (input cache hit rate is about the same,
locality is now worse).
This defaults the policy back to the old one to avoid a regression
but keeps the new one available through an environment variable
OLLAMA_MULTIUSER_CACHE. This is left undocumented as the goal is
to improve this in the future to get the best of both worlds
without user configuration.
For inputs that result in cache misses, on Nvidia/Linux this
change improves performance by 31% for prompt processing and
13% for token generation.
* runner.go: Increase size of response channel
Generally the CPU can easily keep up with handling reponses that
are generated but there's no reason not to let generation continue
and handle things in larger batches if needed.
* llama: Add CI to verify all vendored changes have patches (#7066)
Make sure we don't accidentally merge changes in the vendored code
that aren't also reflected in the patches.
* llama: adjust clip patch for mingw utf-16 (#7065)
* llama: adjust clip patch for mingw utf-16
* llama: ensure static linking of runtime libs
Avoid runtime dependencies on non-standard libraries
* runner.go: Enable llamafile (all platforms) and BLAS (Mac OS)
These are two features that are shown on llama.cpp's system info
that are currently different between the two runners. On my test
systems the performance difference is very small to negligible
but it is probably still good to equalize the features.
* llm: Don't add BOS/EOS for tokenize requests
This is consistent with what server.cpp currently does. It affects
things like token processing counts for embedding requests.
* runner.go: Don't cache prompts for embeddings
Our integration with server.cpp implicitly disables prompt caching
because it is not part of the JSON object being parsed, this makes
the Go runner behavior similarly.
Prompt caching has been seen to affect the results of text completions
on certain hardware. The results are not wrong either way but they
are non-deterministic. However, embeddings seem to be affected even
on hardware that does not show this behavior for completions. For
now, it is best to maintain consistency with the existing behavior.
* runner.go: Adjust debug log levels
Add system info printed at startup and quiet down noisier logging.
* llama: fix compiler flag differences (#7082)
Adjust the flags for the new Go server to more closely match the
generate flow
* llama: refine developer docs (#7121)
* llama: doc and example clean up (#7122)
* llama: doc and example clean up
* llama: Move new dockerfile into llama dir
Temporary home until we fully transition to the Go server
* llama: runner doc cleanup
* llama.go: Add description for Tokenize error case
---------
Co-authored-by: Jesse Gross <jesse@ollama.com>
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
Co-authored-by: Daniel Hiltgen <dhiltgen@users.noreply.github.com>
This change closes the response body when an error occurs in
makeRequestWithRetry. Previously, the first, non-200 response body was
not closed before reattempting the request. This change ensures that
the response body is closed in all cases where an error occurs,
preventing leaks of file descriptors.
Fixes#6974
* Unified arm/x86 windows installer
This adjusts the installer payloads to be architecture aware so we can cary
both amd64 and arm64 binaries in the installer, and install only the applicable
architecture at install time.
* Include arm64 in official windows build
* Harden schedule test for slow windows timers
This test seems to be a bit flaky on windows, so give it more time to converge
* Optimize container images for startup
This change adjusts how to handle runner payloads to support
container builds where we keep them extracted in the filesystem.
This makes it easier to optimize the cpu/cuda vs cpu/rocm images for
size, and should result in faster startup times for container images.
* Refactor payload logic and add buildx support for faster builds
* Move payloads around
* Review comments
* Converge to buildx based helper scripts
* Use docker buildx action for release
* Fix embeddings memory corruption
The patch was leading to a buffer overrun corruption. Once removed though, parallism
in server.cpp lead to hitting an assert due to slot/seq IDs being >= token count. To
work around this, only use slot 0 for embeddings.
* Fix embed integration test assumption
The token eval count has changed with recent llama.cpp bumps (0.3.5+)
The previous value of 64 was WAY too high and unnecessary. It reached
diminishing returns and blew past it. This is a more reasonable number
for _most_ normal cases. For users on cloud servers with excellent
network quality, this will keep screaming for them, without hitting our
CDN limits. For users with relatively poor network quality, this will
keep them from saturating their network and causing other issues.
For simplicity, perform parallelization of embedding requests in the API handler instead of offloading this to the subprocess runner. This keeps the scheduling story simpler as it builds on existing parallel requests, similar to existing text completion functionality.
Commit 1829fb61 ("manifest: Fix crash on startup when trying to clean up
unused files (#5840)") changed the config layer stored in manifests
from a pointer to a value. This was done in order to avoid potential
nil pointer dereferences after it is deserialized from JSON in the
event that the field is missing.
This changes the Layers slice to also be stored by value. This enables
consistency in handling across the two objects.
When creating a model the config layer is appended to the list of
layers and then the last layer is used as the config when writing the
manifest. This change directly uses the config layer to write the
manifest. There is no behavior change but it is less error prone.
Currently if the config field is missing in the manifest file (or
corrupted), Ollama will crash when it tries to read it. This can
happen at startup or when pulling new models.
This data is mostly just used for showing model information so we
can be tolerant of it not being present - it is not required to
run the models. Besides avoiding crashing, this also gives us the
ability to restructure the config in the future by pulling it
into the main manifest file.
If there is an error when opening a manifest file (corrupted, permission denied, etc.)
then the referenced layers will not be included in the list of active
layers. This causes them to be deleted when pruning happens at startup
or a model is pulled.
In such a situation, we should prefer to preserve data in the hopes that
it can be recovered rather than being agressive about deletion.
The file.Truncate call on windows will write the whole file
unless you set the sparse flag, leading to heavy I/O at the
beginning of download. This should improve our
I/O behavior on windows and put less stress on the users disk.
In mult-brand GPU setups, if we couldn't fully load the model we
would fall through the scheduler and mistakenly try to load across
a mix of brands. This makes sure we find the set of GPU(s) that
best fit for the partial load.
This fixes various data races scattered throughout the download/pull
client where the client was accessing the download state concurrently.
This commit is mostly a hot-fix and will be replaced by a new client one
day soon.
Also, remove the unnecessary opts argument from downloadChunk.
This changes the registry client to reuse the original download URL
it gets on the first redirect response for all subsequent requests,
preventing thundering herd issues when hot new LLMs are released.
* Initial Batch Embedding
* Revert "Initial Batch Embedding"
This reverts commit c22d54895a.
* Initial Draft
* mock up notes
* api/embed draft
* add server function
* check normalization
* clean up
* normalization
* playing around with truncate stuff
* Truncation
* Truncation
* move normalization to go
* Integration Test Template
* Truncation Integration Tests
* Clean up
* use float32
* move normalize
* move normalize test
* refactoring
* integration float32
* input handling and handler testing
* Refactoring of legacy and new
* clear comments
* merge conflicts
* touches
* embedding type 64
* merge conflicts
* fix hanging on single string
* refactoring
* test values
* set context length
* clean up
* testing clean up
* testing clean up
* remove function closure
* Revert "remove function closure"
This reverts commit 55d48c6ed1.
* remove function closure
* remove redundant error check
* clean up
* more clean up
* clean up
This change fixes the handling of keep_alive so that if client
request omits the setting, we only set this on initial load. Once
the model is loaded, if new requests leave this unset, we'll keep
whatever keep_alive was there.
Users may not realize the siny new model they're trying to load
fits on their disk, but can't load into system+GPU memory. Today
we crash, but with this fix, we'll give them a better error message
before even trying to load it.
* OpenAI v1 models
* Refactor Writers
* Add Test
Co-Authored-By: Attila Kerekes
* Credit Co-Author
Co-Authored-By: Attila Kerekes <439392+keriati@users.noreply.github.com>
* Empty List Testing
* Use Namespace for Ownedby
* Update Test
* Add back envconfig
* v1/models docs
* Use ModelName Parser
* Test Names
* Remove Docs
* Clean Up
* Test name
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Add Middleware for Chat and List
* Completions Endpoint
* Testing Cleanup
* Test with Fatal
* Add functionality to chat test
* Rename function
* float types
* type cleanup
* cleaning
* more cleaning
* Extra test cases
* merge conflicts
* merge conflicts
* merge conflicts
* merge conflicts
* cleaning
* cleaning
---------
Co-authored-by: Attila Kerekes <439392+keriati@users.noreply.github.com>
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* OpenAI v1 models
* Refactor Writers
* Add Test
Co-Authored-By: Attila Kerekes
* Credit Co-Author
Co-Authored-By: Attila Kerekes <439392+keriati@users.noreply.github.com>
* Empty List Testing
* Use Namespace for Ownedby
* Update Test
* Add back envconfig
* v1/models docs
* Use ModelName Parser
* Test Names
* Remove Docs
* Clean Up
* Test name
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Add Middleware for Chat and List
* Testing Cleanup
* Test with Fatal
* Add functionality to chat test
* OpenAI: /v1/models/{model} compatibility (#5028)
* Retrieve Model
* OpenAI Delete Model
* Retrieve Middleware
* Remove Delete from Branch
* Update Test
* Middleware Test File
* Function name
* Cleanup
* Test Update
* Test Update
---------
Co-authored-by: Attila Kerekes <439392+keriati@users.noreply.github.com>
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
Previously, some costly things were causing the loading of GGUF files
and their metadata and tensor information to be VERY slow:
* Too many allocations when decoding strings
* Hitting disk for each read of each key and value, resulting in a
not-okay amount of syscalls/disk I/O.
The show API is now down to 33ms from 800ms+ for llama3 on a macbook pro
m3.
This commit also prevents collecting large arrays of values when
decoding GGUFs (if desired). When such keys are encountered, their
values are null, and are encoded as such in JSON.
Also, this fixes a broken test that was not encoding valid GGUF.
Until ROCm v6.2 ships, we wont be able to get accurate free memory
reporting on windows, which makes automatic concurrency too risky.
Users can still opt-in but will need to pay attention to model sizes otherwise they may thrash/page VRAM or cause OOM crashes.
All other platforms and GPUs have accurate VRAM reporting wired
up now, so we can turn on concurrency by default.
This adjusts our default settings to enable multiple models and parallel
requests to a single model. Users can still override these by the same
env var settings as before. Parallel has a direct impact on
num_ctx, which in turn can have a significant impact on small VRAM GPUs
so this change also refines the algorithm so that when parallel is not
explicitly set by the user, we try to find a reasonable default that fits
the model on their GPU(s). As before, multiple models will only load
concurrently if they fully fit in VRAM.
* 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>
While models are loading, the VRAM metrics are dynamic, so try
to load on a GPU that doesn't have a model actively loading, or wait
to avoid races that lead to OOMs
Our default behavior today is to try to fit into a single GPU if possible.
Some users would prefer the old behavior of always spreading across
multiple GPUs even if the model can fit into one. This exposes that
tunable behavior.
Still not complete, needs some refinement to our prediction to understand the
discrete GPUs available space so we can see how many layers fit in each one
since we can't split one layer across multiple GPUs we can't treat free space
as one logical block
multiple templates may appear in a model if a model is created from
another model that 1) has an autodetected template and 2) defines a
custom template
Daniel Hiltgen
Blake Mizerany
Jeffrey Morgan
Jesse Gross
Patrick Devine
Alex Mavrogiannis
Tobias Heinze
Michael Yang
Patrick Devine
Richard Lyons
zwwhdls
royjhan
Josh
Daniel Hiltgen
Jitang Lei
Vyacheslav Moskalev
Anatoli Babenia
Tim Scheuermann
Sang Park