* 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>
---------
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>
* cli : auto activate conversation mode if chat template is detected
* add warn on bad template
* update readme (writing with the help of chatgpt)
* update readme (2)
* do not activate -cnv for non-instruct models
Set default width to whatever the terminal is. Also fixed a small bug around
default n_gpu_layers value.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
Related to #10524 / be0e350c references to hipBLAS have been removed
across the repository. This fixes the link from the repositories
`README.md`.
Signed-off-by: Brian 'redbeard' Harrington <redbeard@dead-city.org>
* Add deepseek v1 arch & gigachat template
* improve template code
* add readme
* delete comments
* remove comment
* fix format
* lint llama.cpp
* fix order of deepseek and deepseek2, move gigachat temlate to the end of func
* fix order of deepseek and deepseek2 in constants; mark shared exp as deepseek arch need
* remove comments
* move deepseek above deepseek2
* change placement of gigachat chat template
llama_cpp_canister allows you to run llama.cpp as a Smart Contract on the Internet Computer. The smart contract runs as WebAssembly in a so-called 'canister'.
add intel amx isa detection
add vnni kernel for gemv cases
add vnni and amx kernel support for block_q8_0
code cleanup
fix packing B issue
enable openmp
fine tune amx kernel
switch to aten parallel pattern
add error message for nested parallelism
code cleanup
add f16 support in ggml-amx
add amx kernels for QK_K quant formats: Q4_K, Q5_K, Q6_K and IQ4_XS
update CMakeList
update README
fix some compilation warning
fix compiler warning when amx is not enabled
minor change
ggml-ci
move ggml_amx_init from ggml.c to ggml-amx/mmq.cpp
ggml-ci
update CMakeLists with -mamx-tile, -mamx-int8 and -mamx-bf16
ggml-ci
add amx as an ggml-backend
update header file, the old path for immintrin.h has changed to ggml-cpu-impl.h
minor change
update CMakeLists.txt
minor change
apply weight prepacking in set_tensor method in ggml-backend
fix compile error
ggml-ci
minor change
ggml-ci
update CMakeLists.txt
ggml-ci
add march dependency
minor change
ggml-ci
change ggml_backend_buffer_is_host to return false for amx backend
ggml-ci
fix supports_op
use device reg for AMX backend
ggml-ci
minor change
ggml-ci
minor change
fix rebase
set .buffer_from_host_ptr to be false for AMX backend
* readme: introduce gpustack
GPUStack is an open-source GPU cluster manager for running large
language models, which uses llama.cpp as the backend.
Signed-off-by: thxCode <thxcode0824@gmail.com>
* readme: introduce gguf-parser
GGUF Parser is a tool to review/check the GGUF file and estimate the
memory usage without downloading the whole model.
Signed-off-by: thxCode <thxcode0824@gmail.com>
---------
Signed-off-by: thxCode <thxcode0824@gmail.com>
ramalama is a repo agnostic boring CLI tool that supports pulling from
ollama, huggingface and oci registries.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
