tools : remove llama-run (#18661)

* tools : remove llama-run
* Remove licenses/LICENSE-linenoise

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët 2026-01-07 16:18:26 +01:00 committed by GitHub
parent 56426673cb
commit 56d2fed2b3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
9 changed files with 0 additions and 3659 deletions

View File

@ -482,21 +482,6 @@ To learn more about model quantization, [read this documentation](tools/quantize
</details>
## [`llama-run`](tools/run)
#### A comprehensive example for running `llama.cpp` models. Useful for inferencing. Used with RamaLama [^3].
- <details>
<summary>Run a model with a specific prompt (by default it's pulled from Ollama registry)</summary>
```bash
llama-run granite-code
```
</details>
[^3]: [RamaLama](https://github.com/containers/ramalama)
## [`llama-simple`](examples/simple)
#### A minimal example for implementing apps with `llama.cpp`. Useful for developers.
@ -600,7 +585,6 @@ $ echo "source ~/.llama-completion.bash" >> ~/.bashrc
- [stb-image](https://github.com/nothings/stb) - Single-header image format decoder, used by multimodal subsystem - Public domain
- [nlohmann/json](https://github.com/nlohmann/json) - Single-header JSON library, used by various tools/examples - MIT License
- [minja](https://github.com/google/minja) - Minimal Jinja parser in C++, used by various tools/examples - MIT License
- [linenoise.cpp](./tools/run/linenoise.cpp/linenoise.cpp) - C++ library that provides readline-like line editing capabilities, used by `llama-run` - BSD 2-Clause License
- [curl](https://curl.se/) - Client-side URL transfer library, used by various tools/examples - [CURL License](https://curl.se/docs/copyright.html)
- [miniaudio.h](https://github.com/mackron/miniaudio) - Single-header audio format decoder, used by multimodal subsystem - Public domain
- [subprocess.h](https://github.com/sheredom/subprocess.h) - Single-header process launching solution for C and C++ - Public domain

View File

@ -679,7 +679,6 @@ static void common_params_print_completion(common_params_context & ctx_arg) {
"llama-quantize",
"llama-qwen2vl-cli",
"llama-retrieval",
"llama-run",
"llama-save-load-state",
"llama-server",
"llama-simple",

View File

@ -1,26 +0,0 @@
Copyright (c) 2010-2014, Salvatore Sanfilippo <antirez at gmail dot com>
Copyright (c) 2010-2013, Pieter Noordhuis <pcnoordhuis at gmail dot com>
Copyright (c) 2025, Eric Curtin <ericcurtin17 at gmail dot com>
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

View File

@ -25,7 +25,6 @@ else()
if (LLAMA_BUILD_SERVER)
add_subdirectory(server)
endif()
add_subdirectory(run)
add_subdirectory(tokenize)
add_subdirectory(tts)
add_subdirectory(mtmd)

View File

@ -1,23 +0,0 @@
set(TARGET llama-run)
add_executable(${TARGET} run.cpp linenoise.cpp/linenoise.cpp)
# TODO: avoid copying this code block from common/CMakeLists.txt
set(LLAMA_RUN_EXTRA_LIBS "")
if (LLAMA_CURL)
find_package(CURL REQUIRED)
target_compile_definitions(${TARGET} PUBLIC LLAMA_USE_CURL)
include_directories(${CURL_INCLUDE_DIRS})
set(LLAMA_RUN_EXTRA_LIBS ${LLAMA_RUN_EXTRA_LIBS} ${CURL_LIBRARIES})
endif ()
if(LLAMA_TOOLS_INSTALL)
install(TARGETS ${TARGET} RUNTIME)
endif()
if (CMAKE_SYSTEM_NAME MATCHES "AIX")
# AIX's flock() function comes from libbsd.a
target_link_libraries(${TARGET} PRIVATE -lbsd)
endif()
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT} ${LLAMA_RUN_EXTRA_LIBS})
target_compile_features(${TARGET} PRIVATE cxx_std_17)

View File

@ -1,52 +0,0 @@
# llama.cpp/example/run
The purpose of this example is to demonstrate a minimal usage of llama.cpp for running models.
```bash
llama-run granite3-moe
```
```bash
Description:
Runs a llm
Usage:
llama-run [options] model [prompt]
Options:
-c, --context-size <value>
Context size (default: 2048)
-n, -ngl, --ngl <value>
Number of GPU layers (default: 0)
--temp <value>
Temperature (default: 0.8)
-v, --verbose, --log-verbose
Set verbosity level to infinity (i.e. log all messages, useful for debugging)
-h, --help
Show help message
Commands:
model
Model is a string with an optional prefix of
huggingface:// (hf://), ollama://, https:// or file://.
If no protocol is specified and a file exists in the specified
path, file:// is assumed, otherwise if a file does not exist in
the specified path, ollama:// is assumed. Models that are being
pulled are downloaded with .partial extension while being
downloaded and then renamed as the file without the .partial
extension when complete.
Examples:
llama-run llama3
llama-run ollama://granite-code
llama-run ollama://smollm:135m
llama-run hf://QuantFactory/SmolLM-135M-GGUF/SmolLM-135M.Q2_K.gguf
llama-run huggingface://bartowski/SmolLM-1.7B-Instruct-v0.2-GGUF/SmolLM-1.7B-Instruct-v0.2-IQ3_M.gguf
llama-run ms://QuantFactory/SmolLM-135M-GGUF/SmolLM-135M.Q2_K.gguf
llama-run modelscope://bartowski/SmolLM-1.7B-Instruct-v0.2-GGUF/SmolLM-1.7B-Instruct-v0.2-IQ3_M.gguf
llama-run https://example.com/some-file1.gguf
llama-run some-file2.gguf
llama-run file://some-file3.gguf
llama-run --ngl 999 some-file4.gguf
llama-run --ngl 999 some-file5.gguf Hello World
```

File diff suppressed because it is too large Load Diff

View File

@ -1,137 +0,0 @@
/* linenoise.h -- VERSION 1.0
*
* Guerrilla line editing library against the idea that a line editing lib
* needs to be 20,000 lines of C++ code.
*
* See linenoise.cpp for more information.
*
* ------------------------------------------------------------------------
*
* Copyright (c) 2010-2023, Salvatore Sanfilippo <antirez at gmail dot com>
* Copyright (c) 2010-2013, Pieter Noordhuis <pcnoordhuis at gmail dot com>
* Copyright (c) 2025, Eric Curtin <ericcurtin17 at gmail dot com>
*
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met:
*
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef __LINENOISE_H
#define __LINENOISE_H
#ifdef __cplusplus
extern "C" {
#endif
#include <stddef.h> /* For size_t. */
#include <stdlib.h>
extern const char * linenoiseEditMore;
/* The linenoiseState structure represents the state during line editing.
* We pass this state to functions implementing specific editing
* functionalities. */
struct linenoiseState {
int in_completion; /* The user pressed TAB and we are now in completion
* mode, so input is handled by completeLine(). */
size_t completion_idx; /* Index of next completion to propose. */
int ifd; /* Terminal stdin file descriptor. */
int ofd; /* Terminal stdout file descriptor. */
char * buf; /* Edited line buffer. */
size_t buflen; /* Edited line buffer size. */
const char * prompt; /* Prompt to display. */
size_t plen; /* Prompt length. */
size_t pos; /* Current cursor position. */
size_t oldcolpos; /* Previous refresh cursor column position. */
size_t len; /* Current edited line length. */
size_t cols; /* Number of columns in terminal. */
size_t oldrows; /* Rows used by last refreshed line (multiline mode) */
int history_index; /* The history index we are currently editing. */
};
struct linenoiseCompletions {
size_t len = 0;
char ** cvec = nullptr;
bool to_free = true;
~linenoiseCompletions() {
if (!to_free) {
return;
}
for (size_t i = 0; i < len; ++i) {
free(cvec[i]);
}
free(cvec);
}
};
/* Non blocking API. */
int linenoiseEditStart(struct linenoiseState * l, int stdin_fd, int stdout_fd, char * buf, size_t buflen,
const char * prompt);
const char * linenoiseEditFeed(struct linenoiseState * l);
void linenoiseEditStop(struct linenoiseState * l);
void linenoiseHide(struct linenoiseState * l);
void linenoiseShow(struct linenoiseState * l);
/* Blocking API. */
const char * linenoise(const char * prompt);
void linenoiseFree(void * ptr);
/* Completion API. */
typedef void(linenoiseCompletionCallback)(const char *, linenoiseCompletions *);
typedef const char *(linenoiseHintsCallback) (const char *, int * color, int * bold);
typedef void(linenoiseFreeHintsCallback)(const char *);
void linenoiseSetCompletionCallback(linenoiseCompletionCallback *);
void linenoiseSetHintsCallback(linenoiseHintsCallback *);
void linenoiseSetFreeHintsCallback(linenoiseFreeHintsCallback *);
void linenoiseAddCompletion(linenoiseCompletions *, const char *);
/* History API. */
int linenoiseHistoryAdd(const char * line);
int linenoiseHistorySetMaxLen(int len);
int linenoiseHistorySave(const char * filename);
int linenoiseHistoryLoad(const char * filename);
/* Other utilities. */
void linenoiseClearScreen(void);
void linenoiseSetMultiLine(int ml);
void linenoisePrintKeyCodes(void);
void linenoiseMaskModeEnable(void);
void linenoiseMaskModeDisable(void);
/* Encoding functions. */
typedef size_t(linenoisePrevCharLen)(const char * buf, size_t buf_len, size_t pos, size_t * col_len);
typedef size_t(linenoiseNextCharLen)(const char * buf, size_t buf_len, size_t pos, size_t * col_len);
typedef size_t(linenoiseReadCode)(int fd, char * buf, size_t buf_len, int * c);
void linenoiseSetEncodingFunctions(linenoisePrevCharLen * prevCharLenFunc, linenoiseNextCharLen * nextCharLenFunc,
linenoiseReadCode * readCodeFunc);
#ifdef __cplusplus
}
#endif
#endif /* __LINENOISE_H */

File diff suppressed because it is too large Load Diff