* add glm edge chat model
* use config partial_rotary_factor as rope ratio
* support for glm edge model
* vision model support
* remove debug info
* fix format
* llava.cpp trailing whitespace
* remove unused AutoTokenizer
* Update src/llama.cpp for not contain <|end|> or </s>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* add edge template
* fix chat template
* fix confict
* fix confict
* fix ci err
* fix format err
* fix template err
* 9b hf chat support
* format
* format clip.cpp
* fix format
* Apply suggestions from code review
* Apply suggestions from code review
* Update examples/llava/clip.cpp
* fix format
* minor : style
---------
Co-authored-by: liyuhang <yuhang.li@zhipuai.cn>
Co-authored-by: piDack <pcdack@hotmail.co>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: liyuhang <yuhang.li@aminer.cn>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* An empty tool_call_id is better than none!
* sync: minja (tool call name optional https://github.com/google/minja/pull/36)
* Force-disable parallel_tool_calls if template doesn't support it
* More debug logs
* Llama 3.x tools: accept / trigger on more varied spaced outputs
* Fix empty content for functionary v3.2 tool call
* Add proper tool call docs to server README
* readme: function calling *is* supported now
* Apply suggestions from code review
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
The va_copy man page states that va_end must be called to revert
whatever the copy did. For some implementaions, not calling va_end
has no consequences. For others it could leak memory.
This commit updates the help text for the metrics `requests_processing`
and `requests_deferred` to be more grammatically correct.
Currently the returned metrics look like this:
```console
\# HELP llamacpp:requests_processing Number of request processing.
\# TYPE llamacpp:requests_processing gauge
llamacpp:requests_processing 0
\# HELP llamacpp:requests_deferred Number of request deferred.
\# TYPE llamacpp:requests_deferred gauge
llamacpp:requests_deferred 0
```
With this commit, the metrics will look like this:
```console
\# HELP llamacpp:requests_processing Number of requests processing.
\# TYPE llamacpp:requests_processing gauge
llamacpp:requests_processing 0
\# HELP llamacpp:requests_deferred Number of requests deferred.
\# TYPE llamacpp:requests_deferred gauge
llamacpp:requests_deferred 0
```
This is also consistent with the description of the metrics in the
server examples [README.md](https://github.com/ggerganov/llama.cpp/tree/master/examples/server#get-metrics-prometheus-compatible-metrics-exporter).
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit replaces the two usages of `std::bind` in favor of lambdas for
the callback functions for `callback_new_task` and
`callback_update_slots`.
The motivation for this changes is consistency with the rest of the code
in server.cpp (lambdas are used for all other callbacks/handlers). Also
lambdas are more readable (perhaps this is subjective) but also they are
recommended over `std::bind` in modern C++.
Ref: https://github.com/LithoCoders/dailycpp/blob/master/EffectiveModernC%2B%2B/chapter6/Item34_Prefer_lambdas_to_std::bind.md
This commit updates some of JSON snippets in README.md file and
removes the `json` language tag from the code blocks.
The motivation for this changes is that if there is invalid json in a
code snippet these are highlighted in red which can make it somewhat
difficult to read and can be a little distracting.
* add /apply-template endpoint to server
* remove unnecessary line
* add /apply-template documentation
* return only "prompt" field in /apply-template
* use suggested idea instead of my overly verbose way
* vulkan: initial support for IQ3_S
* vulkan: initial support for IQ3_XXS
* vulkan: initial support for IQ2_XXS
* vulkan: initial support for IQ2_XS
* vulkan: optimize Q3_K by removing branches
* vulkan: implement dequantize variants for coopmat2
* vulkan: initial support for IQ2_S
* vulkan: vertically realign code
* port failing dequant callbacks from mul_mm
* Fix array length mismatches
* vulkan: avoid using workgroup size before it is referenced
* tests: increase timeout for Vulkan llvmpipe backend
---------
Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
* server : update auto gen files comments
This commit updates the 'auto generated files' comments in server.cpp
and removes `deps.sh` from the comment.
The motivation for this change is that `deps.sh` was removed in
Commit 91c36c269b ("server : (web ui)
Various improvements, now use vite as bundler (#10599)").
* squash! server : update auto gen files comments [no ci]
Move comments about file generation to README.md.
* squash! server : update auto gen files comments [no ci]
Remove the comments in server.cpp that mention that information
can be found in the README.md file.
People search for ollama models using the web ui, this change
allows one to copy the url from the browser and for it to be
compatible with llama-run.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
* Add option to not print stack on abort
Add option/envvar to disable stack printing on abort.
Also link some unittests with Threads to fix link errors on
ubuntu/g++11.
* Update ggml/src/ggml.c
---------
Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit enables the `--no-warmup` option for the llama-embeddings.
The motivation for this change is to allow the user to disable the
warmup when running the the program.
The test_completion_stream_with_openai_library() function is actually with stream=False by default, and test_completion_with_openai_library() with stream=True
loops with bounds not known at compile time can not be unrolled.
when ncols_template == 0, the bounds of the loop are not constexpr, thus llvm cant unroll the loops here.
This disables the workaround on rocblas fixed versions (>=4.0.0) to eliminate the runtime cost and unnecessary VRAM allocation of loading all tensile objects.
Implemented ggml_sycl_op_soft_max() F16 src1(mask) support for which a pragma deprecation warning was added during #5021.
To do this, had to decouple it from ggml_sycl_op_flatten which always considered src1 to be of fp32 type(many OP functions are dependent on it).
* SYCL: SOFTMAX F16 mask support and other fixes
* test-backend-ops: Add F16 mask test cases
The HTTP client in llama-run only prints an error in case the download of
a resource failed. If the model name in the CLI parameter list is missing,
this causes the application to crash.
In order to prevent this, a check for the required model parameter has been
added and errors for resource downloads get propagated to the caller.
Signed-off-by: Michael Engel <mengel@redhat.com>
* impl::load change map bpe_ranks to onordered map for reduce time of impl::load on 30%
* llama_model_loader::init_mapping - replace new llama_mmap to std::make_unique<llama_mmap> for clean code & reduce (/2) time of running init_mappings
* Update src/llama-vocab.cpp
---------
Co-authored-by: lexasub <empty@empty.ru>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
This fixes segmentation fault error when running tests when no metal
devices are available (for example, when not linked with Core Graphics
framework or otherwise).
