* 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>
* 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
This adds back a check which was lost many releases back to verify /dev/kfd permissions
which when lacking, can lead to confusing failure modes of:
"rocBLAS error: Could not initialize Tensile host: No devices found"
This implementation does not hard fail the serve command but instead will fall back to CPU
with an error log. In the future we can include this in the GPU discovery UX to show
detected but unsupported devices we discovered.
* Update gpu.md
Seems strange that the laptop versions of 3050 and 3050 Ti would be supported but not the non-notebook, but this is what the page (https://developer.nvidia.com/cuda-gpus) says.
Signed-off-by: bean5 <2052646+bean5@users.noreply.github.com>
* Update gpu.md
Remove notebook reference
---------
Signed-off-by: bean5 <2052646+bean5@users.noreply.github.com>
The v5 hip library returns unsupported GPUs which wont enumerate at
inference time in the runner so this makes sure we align discovery. The
gfx906 cards are no longer supported so we shouldn't compile with that
GPU type as it wont enumerate at runtime.
This also adjusts our algorithm to favor our bundled ROCm.
I've confirmed VRAM reporting still doesn't work properly so we
can't yet enable concurrency by default.
Refine the way we log GPU discovery to improve the non-debug
output, and report more actionable log messages when possible
to help users troubleshoot on their own.
* 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>
* 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>
* docs: add missing instruction for powershell build
The powershell script for building Ollama on Windows now requires the `ThreadJob` module. Add this to the instructions and dependency list.
* Update development.md
* Added instructions to easily install specific versions on faq.md
* Small typo
* Moved instructions on how to install specific version to linux.md
* Update docs/linux.md
* Update docs/linux.md
---------
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* note on naming restrictions
else push would fail with cryptic
retrieving manifest
Error: file does not exist
==> maybe change that in code too
* Update docs/import.md
---------
Co-authored-by: C-4-5-3 <154636388+C-4-5-3@users.noreply.github.com>
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update api.md
Changed the calculation of tps (token/s) in the documentation
* Update docs/api.md
---------
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
This commit introduces a more friendly way to build Ollama dependencies
and the binary without abusing `go generate` and removing the
unnecessary extra steps it brings with it.
This script also provides nicer feedback to the user about what is
happening during the build process.
At the end, it prints a helpful message to the user about what to do
next (e.g. run the new local Ollama).
The recent ROCm change partially removed idempotent
payloads, but the ggml-metal.metal file for mac was still
idempotent. This finishes switching to always extract
the payloads, and now that idempotentcy is gone, the
version directory is no longer useful.
This refines where we extract the LLM libraries to by adding a new
OLLAMA_HOME env var, that defaults to `~/.ollama` The logic was already
idempotenent, so this should speed up startups after the first time a
new release is deployed. It also cleans up after itself.
We now build only a single ROCm version (latest major) on both windows
and linux. Given the large size of ROCms tensor files, we split the
dependency out. It's bundled into the installer on windows, and a
separate download on windows. The linux install script is now smart and
detects the presence of AMD GPUs and looks to see if rocm v6 is already
present, and if not, then downloads our dependency tar file.
For Linux discovery, we now use sysfs and check each GPU against what
ROCm supports so we can degrade to CPU gracefully instead of having
llama.cpp+rocm assert/crash on us. For Windows, we now use go's windows
dynamic library loading logic to access the amdhip64.dll APIs to query
the GPU information.
The linux build now support parallel CPU builds to speed things up.
This also exposes AMD GPU targets as an optional setting for advaced
users who want to alter our default set.
After executing the `userdel ollama` command, I saw this message:
```sh
$ sudo userdel ollama
userdel: group ollama not removed because it has other members.
```
Which reminded me that I had to remove the dangling group too. For completeness, the uninstall instructions should do this too.
Thanks!
This reduces the built-in linux version to not use any vector extensions
which enables the resulting builds to run under Rosetta on MacOS in
Docker. Then at runtime it checks for the actual CPU vector
extensions and loads the best CPU library available
* Clean up documentation
Will probably need to update with PRs for new release.
Signed-off-by: Matt Williams <m@technovangelist.com>
* Correcting to fit in 0.1.15 changes
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* addressing comments
Signed-off-by: Matt Williams <m@technovangelist.com>
* more api cleanup
Signed-off-by: Matt Williams <m@technovangelist.com>
* its llava not llama
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update docs/troubleshooting.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Updated hosting to server and documented all env vars
Signed-off-by: Matt Williams <m@technovangelist.com>
* remove last of the cli descriptions
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* update further per conversation with jeff earlier today
Signed-off-by: Matt Williams <m@technovangelist.com>
* cleanup the doc readme
Signed-off-by: Matt Williams <m@technovangelist.com>
* move upgrade to faq
Signed-off-by: Matt Williams <m@technovangelist.com>
* first change
Signed-off-by: Matt Williams <m@technovangelist.com>
* updated
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update docs/faq.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* examples in parent
Signed-off-by: Matt Williams <m@technovangelist.com>
* add exapmle for create model.
Signed-off-by: Matt Williams <m@technovangelist.com>
* update faq
Signed-off-by: Matt Williams <m@technovangelist.com>
* update create model api
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/faq.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/troubleshooting.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* update the readme in docs
Signed-off-by: Matt Williams <m@technovangelist.com>
* update a few more things
Signed-off-by: Matt Williams <m@technovangelist.com>
* Update docs/troubleshooting.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/faq.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/modelfile.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Update docs/troubleshooting.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
---------
Signed-off-by: Matt Williams <m@technovangelist.com>
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
By default builds will now produce non-debug and non-verbose binaries.
To enable verbose logs in llama.cpp and debug symbols in the
native code, set `CGO_CFLAGS=-g`
- remove ggml runner
- automatically pull gguf models when ggml detected
- tell users to update to gguf in the case automatic pull fails
Co-Authored-By: Jeffrey Morgan <jmorganca@gmail.com>
Bill Wang
Jeffrey Morgan
Daniel Hiltgen
Patrick Devine
Michael
Tomoya Fujita
SnoopyTlion
rayfiyo
Patrick Devine
Michael Yang
Daniel Hiltgen
Bruce MacDonald
Pamela Fox
royjhan
Kyle Kelley
frob
Kim Hallberg
Veit Heller
Tibor Schmidt
Eduard
Napuh
Shubham
alwqx
睡觉型学渣
Carlos Gamez
boessu
CrispStrobe
Jeffrey Chen
Mohamed A. Fouad
Darinka
Adrien Brault
Hyden Liu
Dr Nic Williams
Christian Frantzen
Quinten van Buul
Sri Siddhaarth
Jeremy
Blake Mizerany
Thomas Vitale
John
elthommy
Tristan Rhodes
Tristram Oaten
Robin Glauser
Matt Williams
Cole Gillespie
Daniel Hiltgen
K0IN
pepperoni21