* ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions
* cmake: Add GGML_BMI2 build option
* ggml: enable BMI2 on relevant CPU variants
* ggml-cpu: include BMI2 in backend score
* ggml-cpu: register BMI2 in ggml_backend_cpu_get_features
* ggml-cpu: add __BMI2__ define when using MSVC
-- it might happen if ggml is loaded from 2 separate libraries since each one of them will expose the class. This is more of a guard since we want to use only Metal as embedded library and don't care about the other case.
This commit adds the fetch-depth: 0 option to the checkout action in the
build.yml workflow file (0 meaning that it fetches the complete
history). The default value is 1 when not specified which only fetches
the latest commit.
This is necessary to ensure that `git rev-list --count HEAD` counts the
total number of commits in the history. Currently because the default is
being used the name of the xcframework artifact is always
llama-b1-xcframework.
* sampler: turn lazy grammar trigger words to regexes
* add scripts/tool_bench.sh & .py
* constrain llama json output regardless of function name if matches at beginning
* update relaxed newline space rule in grammar tests
* support add_generation_prompt query parameter (useful for /apply_template)
* Update src/llama-grammar.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
The commit add the name parameter to the upload-artifact action to
ensure that the artifact is uploaded with the correct name.
The motivation for this is that currently the uploaded xcframework
is named as llama-b1-xcframework.zip. With this change the name of this
artifact should contain the build number like the other artifacts.
* ci : remove xframework upload
This commit removes the upload of the xframework zip file as an
artifact.
The motivation for this change is that the xframework zip file is
currently being uploaded as part of strategy and will therefore be
attempted to be uploaded multiple times and will fail the build.
The uploading should be moved to somewhere else in the build to avoid
this.
* ci : add xcframework upload to macos-latest job
The first kv shift offsets the positions of all tokens after head_c.
When using llama_kv_cache_seq_rm next, using head_c will remove the valid tokens because their positions have already been offset.
* llama : add xcframework build script
This commit adds a script to build an XCFramework for Apple
ios, macos, visionos, and tvos platforms.
The generated XCFramework can then be added to a project and used in
the same way as a regular framework. The llama.swiftui example project
has been updated to use the XCFramework and can be started using the
following command:
```console
$ open examples/llama.swiftui/llama.swiftui.xcodeproj/
```
Refs: https://github.com/ggml-org/llama.cpp/issues/10747
* examples : remove llama.cpp (source dir ref) from project.pbxproj
This commit removes the reference to llama.cpp from the project.pbxproj
file since Package.swift has been removed.
* ci : updated build.yml to use build-xcframework.sh
* ci : add xcframework build to github releases
This commit adds the ability to create a GitHub release with the
xcframework build artifact.
* scripts : add apple app validation scripts
This commit adds scripts that can validate the iOS, macOS, tvOS, and
VisionOS applications. The scripts create a simple test app project,
copy the llama.xcframework to the test project, build and archive the
app, create an IPA from the archive, and validate the IPA using altool.
The motivation for this is to provide some basic validation and
hopefully avoid having to manually validate apps in Xcode.
* llama : remove Package.swift
This commit removes the Package.swift file, as we are now building an
XCFramework for the project.
* llama : remove Sources and spm-headers directories
* llama : use TargetConditionals.h for visionOS/tvOS
* Add include files for std::min/max and std::toupper/tolower
* win32: move _USE_MATH_DEFINES before includes to ensure M_PI is defined
* Use GGML_RESTRICT instead of "restrict" keyword everywhere, and use "__restrict" in MSVC plain C mode
* win32: only use __restrict in MSVC if C11/C17 support is not enabled
---------
Co-authored-by: Marcus Groeber <Marcus.Groeber@cerence.com>
* Add chat template formatting to -no-cnv
* only enable prompt formatting if explicitly enabled
* add -st / --single-turn
* add --single-turn and -p in conversation mode
* fix -sys + -p
* reword warning
* small readability change and fix (long) outdated example usage
* only activate single turn in conversation mode
Adds GGML_HIP_ROCWMMA_FATTN and rocwmma header check
Adds rocWMMA support to fattn-wmma-f16
---
Signed-off-by: Carl Klemm <carl@uvos.xyz>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Ben Jackson <ben@ben.com>
* Support fp16 unary operations in the CUDA backend
* cpu: increase fp16 support for unary operators in the CPU backend
* cuda: increase fp16 support for unary operators in the CUDA backend
* Add test cases for fp16 unary operators
* metal: update supports_op for unary operators that don't support fp16, to prevent test-backend-ops from failing
* metal: fix PR comments for unary op support after fp16 unary tests
* Support float16-to-float16 add/sub/mul/div operations in the CUDA backend
* Add fp16 support for add/sub/mul/div on the CPU backend
* Add test cases for fp16 add/sub/mul/div
This commit tries to address/improve an issue with the server tests
which are failing with a timeout. Looking at the logs it seems like
they are timing out after 12 seconds:
```
FAILED unit/test_chat_completion.py::test_completion_with_json_schema[False-json_schema0-6-"42"] - TimeoutError: Server did not start within 12 seconds
```
This is somewhat strange as in utils.py we have the following values:
```python
DEFAULT_HTTP_TIMEOUT = 12
if "LLAMA_SANITIZE" in os.environ or "GITHUB_ACTION" in os.environ:
DEFAULT_HTTP_TIMEOUT = 30
def start(self, timeout_seconds: int | None = DEFAULT_HTTP_TIMEOUT) -> None:
```
It should be the case that a test running in a github action should have
a timeout of 30 seconds. However, it seems like this is not the case.
Inspecting the logs from the CI job we can see the following environment
variables:
```console
Run cd examples/server/tests
2 cd examples/server/tests
3 ./tests.sh
4 shell: /usr/bin/bash -e {0}
5 env:
6 LLAMA_LOG_COLORS: 1
7 LLAMA_LOG_PREFIX: 1
8 LLAMA_LOG_TIMESTAMPS: 1
9 LLAMA_LOG_VERBOSITY: 10
10 pythonLocation: /opt/hostedtoolcache/Python/3.11.11/x64
```
This probably does not address the underlying issue that the servers
that are providing the models to be downloaded occasionally take a
longer time to response but might improve these situations in some
cases.
* Use jinja chat template system prompt by default
* faster conditional order
* remove nested ternary
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* fix typos and improve menu text clarity
* rename variable trimedValue to trimmedValue
* add updated index.html.gz
* rebuild
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* Upgrade init_tensor API to return a ggml_status
To prepare for an 'abort-free' ggml
(ggml not to abort on OOMs but return a OOM status),
as agreeed with Diego in the ggml repo,
upgrade the init_tensor() and view_init() APIs
to return a ggml_status.
* misc fixes
---------
Co-authored-by: slaren <slarengh@gmail.com>
* Added Phi-4-mini-instruct support
* Update regex per ngxson
* Change the vocab base to Xenova/gpt-4o
* fix conversion update script
* no need to check longrope
* minor style fix
* fix python style
---------
Co-authored-by: Nicholas Sparks <nisparks@microsoft.com>
* vulkan: implement specialized MMV kernels for IQ2 quantizations
* vulkan: add MMV kernels for IQ3 quants
* vulkan: Increase MMV batch size and unroll IQ LUT setup
* vulkan: fix init_iq_shmem for WG sizes larger than tables
* vulkan: common batch size for all I-quants
* Added SVE Support for Q2_K Quantized Models
* Use 4-space indentation in the switch cases
* removed comments lines
* Remove the loop Retain the curly bracess for better understanding of code
* Remove the comment like added for q3_k_q8_k kernel
---------
Co-authored-by: vithulep <p.m.vithule1517@gmail.com>
* Fix dependencies between ggml and backends
ggml backends link only to ggml-base and ggml links to all backends.
* Fix installation of ggml backends
Set up GNUInstallDirs before setting the installation directory of ggml backends
* Refactor gguf scripts to improve metadata handling
Added contents method to ReaderField class
Added endianess property to GGUFReader class
* update scripts
* fix import
* remove unused import
* attempt to work around flake and pyright errors
* second attempt
* give up, ignore type
* bump version
* apply newbyteorder fixes
Currently self.byte_order is never used.
Actually use it to byteswap read data to
allow reading big endian files on little endian systems
and vice versa.
Now it's possible to convert little-endian model
into a big-endian model and back
on a little-endian system.
It's useful to be able to have this from the library layer as it's a key
parameter of the model (e.g. to figure out how much KV cache memory is
needed).
* opt performance by reorder for Intel GPU
* detect hw type and save opt feature, and print opt feature
* correct name
* support optimize graph once when compute graph, record the opt status in tensor->extra, make CI passed
* add env variable GGML_SYCL_DISABLE_OPT for debug
* use syclex::architecture replace the custom hw define, update the guide for GGML_SYCL_DISABLE_OPT
* add performance data
* mv getrows functions to separeted files
* fix global variables
---------
Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>
Use consolidated open function call from File class. Change
read_all to to_string(). Remove exclusive locking, the intent for
that lock is to avoid multiple processes writing to the same file,
it's not an issue for readers, although we may want to consider
adding a shared lock. Remove passing nullptr as reference,
references are never supposed to be null. clang-format the code
for consistent styling.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
* llava: export function `clip_build_img_from_pixels` to build image from pixels decoded by other libraries instead of stb_image.h for better performance
* Apply suggestions from code review
---------
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
The commit updates the help view in the llama.swiftui example to use a
NavigationView and a Done button to dismiss the help view.
The motivation for this is that without this change there is now way to
dimiss the help view.
* MUSA: support ARM64 and enable __dp4a .etc
* fix cross entropy loss op for musa
* update
* add cc info log for musa
* add comment for the MUSA .cc calculation block
---------
Co-authored-by: Bodhi Hu <huaishun.hu@mthreads.com>
* ggml-cpu: Add CPU backend support for KleidiAI library
* Add environmental variable GGML_KLEIDIAI_SME
* Add support for multithread LHS conversion
* Switch kernel selection order to dotprod and i8mm
* updates for review comments
* More updates for review comments
* Reorganize and rename KleidiAI files
* Move ggml-cpu-traits.h to source file
* Update cmake for SME build and add alignment for SME
* Remove append GGML_USE_CPU_KLEIDIAI to the GGML_CDEF_PUBLIC list
Relates to: https://github.com/ggml-org/llama.cpp/issues/11178
Added --chat-template-file CLI option to llama-run. If specified, the file
will be read and the content passed for overwriting the chat template of
the model to common_chat_templates_from_model.
Signed-off-by: Michael Engel <mengel@redhat.com>
This commit adds a preset for llama.vim to use the default Qwen 2.5
Coder models.
The motivation for this change is to make it easier to start a server
suitable to be used with the llama.vim plugin. For example, the server
can be started with a command like the following:
```console
$ llama.vim --fim-qwen-1.5b-default
```
Refs: https://github.com/ggml-org/llama.cpp/issues/10932
This commit adjusts the indentation for the functions `parse_sequence`
and `parse_rule` in src/llama-grammar.cpp.
The motivation is consistency and improve readability.
* Webui: Enable communication with parent html (if webui is in iframe):
- Listens for "setText" command from parent with "text" and "context" fields. "text" is set in inputMsg, "context" is used as hidden context on the following requests to the llama.cpp server
- On pressing na Escape button sends command "escapePressed" to the parent
Example handling from the parent html side:
- Send command "setText" from parent html to webui in iframe:
const iframe = document.getElementById('askAiIframe');
if (iframe) {
iframe.contentWindow.postMessage({ command: 'setText', text: text, context: context }, '*');
}
- Listen for Escape key from webui on parent html:
// Listen for escape key event in the iframe
window.addEventListener('keydown', (event) => {
if (event.key === 'Escape') {
// Process case when Escape is pressed inside webui
}
});
* Move the extraContext from storage to app.context.
* Fix formatting.
* add Message.extra
* format + build
* MessageExtraContext
* build
* fix display
* rm console.log
---------
Co-authored-by: igardev <ivailo.gardev@akros.ch>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* server : add TEI API format for /rerank endpoint
* Apply suggestions from code review
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* fix
* also gitignore examples/server/*.gz.hpp
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit fixes an issue in the llama.cpp project where the command for testing the llama-server object contained a duplicated file extension. The original command was:
./tests.sh unit/test_chat_completion.py.py -v -x
It has been corrected to:
./tests.sh unit/test_chat_completion.py -v -x
This change ensures that the test script correctly locates and executes the intended test file, preventing test failures due to an incorrect file name.
Rémy O