GitLab

Llama.cpp sometimes returns NULL as a return value to report an
error. We should explicitly check for this and convert it to a Go
error rather than putting NULL in our data structures and waiting
for it to blow up later.

Co-authored-by: jmorganca <jmorganca@gmail.com>
Co-authored-by: Michael Yang <mxyng@pm.me>
Co-authored-by: Jesse Gross <jesse@ollama.com>

* fix(ext_server): Port llama.cpp sampling refactors to ext_server

This was a fairly large changeset. I closely followed the changes here:
https://github.com/ggerganov/llama.cpp/commit/df270ef74596da8f1178f08991f4c51f18c9ee82



Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(server.cpp): Refactor server.cpp logging for llama.cpp overhaul

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Bump llama.cpp to the latest master with `granite` support

This does not yet have granite MoE support, but that can come in a
follow up PR

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(patches): Update all patches (except solar-pro) to work with bumped llama.cpp

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(solar): Update solar patch for llama.cpp bump

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama.cpp): Bump llama.cpp for granitemoe support

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama.cpp): Bump llama.cpp for granitemoe support

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(solar): Update the solar-pro patch for latest llama.cpp bump

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama.cpp): Bump to the latest master of llama.cpp

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(patches): Update all patches for latest bump

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama): Always run sync.sh from the right directory

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama/patches): Update llama patches

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama)!: Rough sync with llama.cpp submodule

There are a number of changes that will need to be propagated to llama.go
before any of this works!

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama/patches): Add a patch and update for missing ggml-impl.h include

This include is where the ggml_cgraph struct is defined. It is included in
many of the .c files to define the forward declartion in ggml.h. It seems
that with the subset of code included here, the import was somehow lost (or
out-of-order) when building, so adding this include to llama.cpp fixes the
missing definition.

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama/sync): Add missing ggml-cpu-impl.h copy-over in sync.sh

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Add missing log.cpp

This was added as part of the logging overhaul done in llama.cpp

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Overhaul use of sampling module for llama.cpp changes

The changes here reflect the changes made in the big llama.cpp sampling PR
https://github.com/ggerganov/llama.cpp/pull/9294



The sampling functionality is now broken into the base interface
(llama_sampler) and the generation implementation (gpt_sampler). The
changes here reflect that. Since the sampling.h/sampling.cpp code uses c++
STL headers, the sampling_ext.[h|cpp] wrapper is maintained to allow go to
access a pure-C interface.

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Fix the impl of SampleTokenGreedy for new sampling

I don't think this method is currently used, so it could probably just be
removed so that all sampling goes through the GPT interface, but in the
interest of doing no harm, this should keep the method working as expected.

Branch: IBMGraniteArchitectureSupport

* fix(llama): Remove unused SampleTokenGreedy

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(sync): Remove bash-specific change to sync.sh

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* chore(gofumpt): Format on llama.go to pass linting

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llm): Fix missing <thread> include in ext_server

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Remove TODO about grammar_first

This feature was not used/needed previously so should be fine without
plumbing it through now.

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Better naming for sampling wrapper and args

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Fix patch 05 to use new wrapper api and re-sync

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* runner: Flush pending responses before returning

If there are any pending reponses (such as from potential stop
tokens) then we should send them back before ending the sequence.
Otherwise, we can be missing tokens at the end of a response.

Fixes #6707

* fix(llama/sampling): Use gpt_sampler with a forward declaration

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Remove unnecessary patch for gguf impl header

This was caused by an earlier mistake in the embeddings patch that was
dereferencing the pointer instead of using the wrapper API.

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llm): Remove use of deprecated --log-disable flag

Branch: IBMGraniteArchitectureSupport
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

Cleaning up go package naming

On windows, detect large multi-socket systems and reduce to the number of cores
in one socket for best performance

Close can be called on an LLM server if the runner subprocess dies.
However, the Ollama scheduler code may not know about this yet and
still try to access it. In this case, it is important that 'cmd'
is still available as it is used to check on the status of the
subprocess. If this happens, Kill may be called twice on the subprocess -
that is fine.

In addition, model unloading may race with new accesses, so we should
hold a lock around this. This may result in the model being reloaded
after the first close call - this is also fine as close will be called
again later.

* 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>

* 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

* Quiet down dockers new lint warnings

Docker has recently added lint warnings to build.  This cleans up those warnings.

* Fix go lint regression

With the new very large parameter models, some users are willing to wait for
a very long time for models to load.

On systems with low system memory, we can hit allocation failures that are difficult to diagnose
without debug logs.  This will make it easier to spot.

The numa flag may be having a performance impact on multi-socket systems with GPU loads

This adjusts linux to follow a similar model to windows with a discrete archive
(zip/tgz) to cary the primary executable, and dependent libraries. Runners are
still carried as payloads inside the main binary

Darwin retain the payload model where the go binary is fully self contained.

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.

Don't allow loading models that would lead to memory exhaustion (across vram, system memory and disk paging). This check was already applied on Linux but should also be applied on Windows as well.

If the system has multiple numa nodes, enable numa support in llama.cpp
If we detect numactl in the path, use that, else use the basic "distribute" mode.

* add prompt tokens to embed response

* rm slog

* metrics

* types

* prompt n

* clean up

* reset submodule

* update tests

* test name

* list metrics

Make sure if something goes wrong spawning the process, the user gets
enough info to be able to try to self correct, or at least file a bug
with details so we can fix it.  Once the process starts, we immediately
change back to the recommended setting to prevent the blocking dialog.
This ensures if the model fails to load (OOM, unsupported model type,
etc.) the process will exit quickly and we can scan the stdout/stderr
of the subprocess for the reason to report via API.

On windows, the exit status winds up being the search term many
users search for and end up piling in on issues that are unrelated.
This refines the reporting so that if we have a more detailed message
we'll suppress the exit status portion of the message.

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.

* Initial Batch Embedding

* Revert "Initial Batch Embedding"

This reverts commit c22d54895a280b54c727279d85a5fc94defb5a29.

* 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 55d48c6ed17abe42e7a122e69d603ef0c1506787.

* remove function closure

* remove redundant error check

* clean up

* more clean up

* clean up

* llm: avoid loading model if system memory is too small

* update log

* Instrument swap free space

On linux and windows, expose how much swap space is available
so we can take that into consideration when scheduling models

* use `systemSwapFreeMemory` in check

---------
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>

llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535)

ensure runtime model changes (template, system prompt, messages,
options) are captured on model updates without needing to reload the
server

When ollama is running a long time, tmp cleaners can remove the
runners.  This tightens up a few corner cases on arm macs where
we failed with "server cpu not listed in available servers map[]"

This uses nil as undefined for a cleaner implementation.

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.

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.

If we try to use mmap when the model is larger than the system free space, loading is slower than the no-mmap approach.